15 MiMo-V2.6-Pro Xiaomi 79±1 local ~443GB 1M llama.cpp › copy 16 Hy4 preview (770B-A49B) Tencent 79±1 local ~248GB 1M llama.cpp › copy 18 Qwen3.8 Max (2.4T-A95B) Alibaba 78±1 local ~380GB 262k llama.cpp › copy +2 21 DeepSeek V4.1 Flash DeepSeek 78±1 local ~537GB 1M how to run › copy 25 Kimi K3 Moonshot AI 77±1 local ~884GB 1M llama.cpp › copy +6 27 MiMo-V2.6-Flash (309B-A15B) Xiaomi 77±1 local ~136GB 1M llama.cpp › copy 31 DeepSeek V4 Pro (0813) DeepSeek 76±1 local ~1010GB 1M llama.cpp › copy +2 33 GLM-5.3 Z.ai 76±1 local ~239GB 1M llama.cpp › copy 36 DeepSeek V4 Flash Vision (Exp) DeepSeek 76±2 local ~104GB 1M llama.cpp › copy 37 Qwen3.8-Flash-Next Alibaba 75±1 local ~59GB 262k llama.cpp › copy 50 DeepSeek V4 Flash (0731) DeepSeek 74±1 local ~92GB 1M llama.cpp › copy +2 52 GLM-5.3-Flash Z.ai 74±1 local ~103GB 1M llama.cpp › copy +2 55 Hunyuan Hy3 (295B-A21B) Tencent 74±1 local ~96GB 256k llama.cpp › copy 57 GLM-5.2 Z.ai 74±1 local ~121GB 1M llama.cpp › copy +6 59 Qwen3.8 27B Alibaba 73±1 local ~18GB 262k LM Studio › copy +3 61 Kimi K2.6 Moonshot AI 73±1 local ~317GB 262k llama.cpp › copy +11 63 LongCat 2.0 (1.6T-A48B) Meituan 73±2 local ~2155GB 1M how to run › copy 69 DeepSeek V4 Pro (Preview, Apr 2026) DeepSeek 72±1 local ~604GB llama.cpp › copy +6 72 Kimi K2.7 Code Moonshot AI 72±1 local ~359GB 262k llama.cpp › copy 73 DeepSeek V4 Flash (Preview, Apr 2026) DeepSeek 72±1 local ~103GB llama.cpp › copy +4 75 Solar Open 2 (250B-A15B) Upstage 72±1 † local ~527GB 1M how to run › copy 78 Ling 3.0 Flash (124B-A5B) inclusionAI (Ant Group) 71±2 † local ~75GB 131k LM Studio › copy 81 GLM-5.1 Z.ai 71±1 local ~119GB 200k llama.cpp › copy +11 82 Qwen3.5 397B-A17B Alibaba 71±0 local ~65GB 262k llama.cpp › copy +15 83 Ornith 1.5 35B-A3B DeepReinforce 71±2 † local ~22GB 262k LM Studio › copy 84 MiniMax-M3 MiniMax 70±1 local ~137GB 1M llama.cpp › copy +2 88 KAT-Coder-V2.5-Dev (35B-A3B) Kuaishou (Kwaipilot) 70±2 † local ~22GB 262k LM Studio › copy 90 Inkling Small (266B-A12B) Thinking Machines 70±1 local ~86GB 1M llama.cpp › copy 92 Kimi K2.5 Moonshot AI 70±1 local ~160GB 262k llama.cpp › copy +15 93 GLM-5 Z.ai 70±1 local ~119GB 205k llama.cpp › copy +11 95 MiMo-V2.5-Pro (1T-A42B) Xiaomi 70±1 local ~163GB 1M llama.cpp › copy 96 Inkling (975B-A41B) Thinking Machines 70±1 local ~156GB 1M llama.cpp › copy 97 Muse Glimmer 30B Meta 70±1 local ~19GB 131k llama.cpp › copy 98 Nemotron 3 Ultra 550B-A55B NVIDIA 69±1 local ~89GB 1M llama.cpp › copy 99 Qwen3.6 27B Alibaba 69±1 local ~18GB 262k LM Studio › copy +4 101 A.X K2 (688B-A33B) SK Telecom 69±1 † local ~1454GB 262k how to run › copy 103 MiMo-V2.5 (310B-A15B) Xiaomi 69±1 local ~100GB 1M llama.cpp › copy 105 Qwen3.5 122B-A10B Alibaba 69±1 local ~75GB 262k LM Studio › copy +5 107 GLM-4.7 Z.ai 69±1 local ~58GB 205k llama.cpp › copy +5 111 Qwen3.5 27B Alibaba 69±0 local ~18GB 262k LM Studio › copy +8 115 Step 3.5 Flash (196B-A11B) StepFun 68±1 local ~118GB 256k LM Studio › copy 116 DeepSeek V3.2 DeepSeek 68±1 local ~110GB 128k llama.cpp › copy +15 120 MiniMax-M2.7 MiniMax 68±1 local ~75GB 205k llama.cpp › copy +2 121 Qwen3.6 35B-A3B Alibaba 68±1 local ~23GB 262k LM Studio › copy +4 122 Ornith 1.0 35B (35B-A3B) DeepReinforce 68±1 local ~23GB 262k LM Studio › copy 123 Hy3 preview (295B-A21B) Tencent 68±1 local ~629GB how to run › copy 127 K-EXAONE 2.0 (750B-A37B) LG AI Research 67±1 † local ~791GB 262k how to run › copy 129 Kimi K2 Thinking Moonshot AI 67±1 local ~160GB 262k llama.cpp › copy 130 Laguna M.1 Poolside 67±2 local ~135GB 262k LM Studio › copy 132 Step 3.7 Flash (198B-A11B) StepFun 67±1 local ~104GB 256k llama.cpp › copy 133 Gemma 4 31B Google 67±1 local ~21GB 262k LM Studio › copy +20 135 Qwen3-Coder-Next (80B-A3B) Alibaba 67±2 local ~27GB 262k llama.cpp › copy 138 GigaChat 3.5 Ultra Reasoning (432B-A28B) Sber 67±1 † local ~461GB 262k how to run › copy 139 Qwen3.5 35B-A3B Alibaba 67±0 local ~23GB 262k LM Studio › copy +12 140 DeepSeek V3.1 Terminus DeepSeek 67±1 local ~230GB 164k llama.cpp › copy 141 DeepSeek V3.2 Exp DeepSeek 67±1 local ~726GB how to run › copy 142 Qwen3 235B-A22B Thinking 2507 Alibaba 66±1 local ~76GB 131k llama.cpp › copy +6 146 MiMo-V2-Flash (309B-A15B) Xiaomi 66±1 local ~108GB llama.cpp › copy 147 GLM-4.6 Z.ai 66±1 local ~58GB 205k llama.cpp › copy +1 148 Kimi K2 Instruct (0711) Moonshot AI 66±1 local ~160GB 131k llama.cpp › copy +3 150 MiniMax-M2.5 MiniMax 66±1 local ~75GB 205k llama.cpp › copy +3 152 DeepSeek V3.1 DeepSeek 66±1 local ~110GB 131k llama.cpp › copy +3 153 Spark-X2.5 4B iFLYTEK (SparkLLM) 66±1 † local ~3.9GB 1M LM Studio › copy 154 MiniMax-M2.1 MiniMax 66±1 local ~79GB llama.cpp › copy 155 Nemotron Cascade 2 30B-A3B NVIDIA 66±1 local ~20GB 256k LM Studio › copy 156 Laguna XS 2.1 (33B-A3B) Poolside 66±2 † local ~21GB 262k LM Studio › copy 157 LongCat-Flash-Chat (560B-A27B) Meituan 66±1 local ~333GB 128k LM Studio › copy 161 MiMo-V2.6-Distill-Qwen-9B Xiaomi 65±2 † local ~7.8GB LM Studio › copy 162 K-EXAONE (236B-A23B) LG AI Research 65±1 local ~152GB 262k llama.cpp › copy 163 DeepSeek R1 0528 DeepSeek 65±1 local ~110GB 164k llama.cpp › copy +6 164 EXAONE 4.5 33B LG AI Research 65±2 † local ~24GB 262k llama.cpp › copy 167 INTELLECT-3 Prime Intellect 65±1 local ~48GB llama.cpp › copy 168 Nemotron 3 Super 120B-A12B NVIDIA 65±1 local ~73GB 262k LM Studio › copy 169 GLM-4.5 Z.ai 65±1 local ~58GB 131k llama.cpp › copy +3 171 MiniMax-M2 MiniMax 65±1 local ~75GB 205k llama.cpp › copy 172 Laguna XS.2 Poolside 65±2 local ~21GB 262k LM Studio › copy 173 Qwen3 235B-A22B Instruct 2507 Alibaba 65±1 local ~76GB 262k llama.cpp › copy +3 174 Mistral Medium 3.5 (128B) Mistral 65±1 local ~42GB 262k llama.cpp › copy 175 Command A+ (05-2026) Cohere 64±1 local ~71GB 128k llama.cpp › copy 177 Nemotron-Labs-3 Puzzle 75B-A9B NVIDIA 64±1 † local ~35GB llama.cpp › copy 178 Qwen3-VL 235B-A22B Thinking Alibaba 64±1 local ~111GB 256k LM Studio › copy 179 Qwen3-Coder 480B-A35B Instruct Alibaba 64±1 local ~78GB 262k llama.cpp › copy 181 Gemma 4 26B-A4B Google 64±1 local ~18GB 262k LM Studio › copy +12 182 Kimi K2 Instruct (0905) Moonshot AI 64±2 local ~298GB llama.cpp › copy 183 Qwen3-VL 235B-A22B Instruct Alibaba 64±1 local ~134GB 256k LM Studio › copy 186 MiniCPM5 2B OpenBMB 64±1 † local ~3GB 131k LM Studio › copy 188 Qwen3-Next 80B-A3B Thinking Alibaba 63±1 local ~27GB 131k llama.cpp › copy +3 189 DeepSeek R1 (Jan '25) DeepSeek 63±1 local ~110GB 128k llama.cpp › copy +15 191 Qwen3-Next 80B-A3B Instruct Alibaba 63±1 local ~27GB 131k llama.cpp › copy 192 Granite 4.2 30B IBM 63±1 local ~19GB 131k LM Studio › copy 195 GLM-4.5-Air Z.ai 63±1 local ~35GB 131k llama.cpp › copy +3 196 Qwen3.5 9B Alibaba 63±1 local ~7.4GB 262k llama.cpp › copy +17 197 Seed-OSS 36B Instruct ByteDance Seed 63±1 local ~23GB 524k LM Studio › copy 199 Trinity-Large-Thinking Arcee AI 63±2 local ~141GB 512k llama.cpp › copy 201 MiniMax-M1 (80k) MiniMax 62±1 local ~959GB 1M how to run › copy 202 Gemma 4 12B Google 62±1 local ~8.5GB 262k LM Studio › copy 204 Nemotron 3.5 Lightning 30B-A3B NVIDIA 62±2 local ~20GB 262k LM Studio › copy 205 GLM-4.6V Z.ai 62±2 local ~51GB 128k llama.cpp › copy 206 Devstral 2 (2512) Mistral 62±2 local ~75GB 256k LM Studio › copy 208 A.X K1 (519B-A33B) SK Telecom 62±1 † local ~1091GB how to run › copy 209 gpt-oss-120b OpenAI 62±1 local ~67GB 131k llama.cpp › copy +19 211 Qwen3-VL 32B Thinking Alibaba 62±1 local ~22GB 256k LM Studio › copy 213 Mistral Large 3 (675B-A41B) Mistral 62±1 local ~108GB 262k llama.cpp › copy +1 214 Apriel 1.6 15B Thinker ServiceNow 62±2 † local ~10GB LM Studio › copy 219 GLM-4.5V Z.ai 61±2 local ~69GB 64k llama.cpp › copy 220 Llama 3.1 Nemotron Ultra 253B v1 NVIDIA 61±2 local ~82GB 128k llama.cpp › copy 222 Devstral Small 2 24B Mistral 61±3 † local ~17GB 262k llama.cpp › copy 225 Qwen3 30B-A3B Thinking 2507 Alibaba 61±1 local ~20GB 262k LM Studio › copy +8 226 Qwen3.5 4B Alibaba 61±1 local ~4.3GB 262k llama.cpp › copy +10 227 Nemotron-Cascade-14B-Thinking NVIDIA 61±1 † local ~10GB LM Studio › copy 228 Mellum2.1 12B-A2.5B Thinking JetBrains 60±2 † local ~8.3GB LM Studio › copy 230 DeepSeek V3 0324 DeepSeek 60±1 local ~108GB 164k llama.cpp › copy +11 231 Qwen3 30B-A3B Instruct 2507 Alibaba 60±1 local ~20GB 262k LM Studio › copy +4 232 Qwen3-VL 32B Instruct Alibaba 60±1 † local ~22GB 256k LM Studio › copy 233 Falcon-H1R 7B TII 60±1 † local ~6GB 262k LM Studio › copy 235 ERNIE 4.5 300B-A47B Baidu 60±1 † local ~97GB 131k llama.cpp › copy 237 Qwen3 235B-A22B (Apr 2025, hybrid) Alibaba 60±1 local ~76GB 131k llama.cpp › copy +14 239 Granite 4.2 8B IBM 60±1 local ~6.6GB 131k LM Studio › copy 240 Solar Open 100B (102B-A12B) Upstage 60±1 † local ~41GB 131k llama.cpp › copy 241 Qwen3-VL 30B-A3B Thinking Alibaba 60±1 † local ~21GB 256k LM Studio › copy 242 Mistral Small 4 (119B-A6.5B) Mistral 60±2 local ~40GB 262k llama.cpp › copy 244 QwQ-32B Alibaba 59±1 local ~21GB 131k LM Studio › copy +7 245 OpenReasoning-Nemotron-32B NVIDIA 59±2 † local ~21GB LM Studio › copy 246 DeepSeek V3 (Dec '24) DeepSeek 59±1 local ~337GB 131k llama.cpp › copy +10 247 Gemma 2 9B IT SimPO Princeton NLP 59±1 local ~7.6GB llama.cpp › copy 248 Gemma 2 9B IT DPO (Princeton) Princeton NLP 59±1 local ~7.6GB llama.cpp › copy 249 Trinity-Large-Preview Arcee AI 59±2 local ~155GB llama.cpp › copy 250 GLM-4.7-Flash Z.ai 59±1 local ~19GB 200k LM Studio › copy 251 EXAONE 4.0 32B LG AI Research 59±1 local ~20GB 131k LM Studio › copy 252 Phi-4-reasoning-plus 14B Microsoft 59±1 local ~10GB LM Studio › copy 253 Nemotron-Cascade-8B NVIDIA 59±1 † local ~6.3GB LM Studio › copy 254 Qwen3 14B Alibaba 59±1 local ~10GB 33k LM Studio › copy +6 257 gpt-oss-20b OpenAI 58±1 local ~14GB 131k llama.cpp › copy +15 258 Llama 3.3 Nemotron Super 49B v1 NVIDIA 58±2 local ~22GB llama.cpp › copy 259 Olmo 3.1 32B Think Ai2 58±1 local ~21GB 66k LM Studio › copy 260 DeepSeek R1 Distill Llama 70B DeepSeek 58±1 local ~30GB 131k llama.cpp › copy +1 261 Phi-4-reasoning 14B Microsoft 58±1 local ~10GB 33k LM Studio › copy 262 Olmo 3 32B Think Ai2 58±1 local ~21GB 66k LM Studio › copy 263 Magistral Small 1.2 Mistral 58±1 local ~16GB 131k LM Studio › copy 264 Nemotron-Cascade-8B-Thinking NVIDIA 58±2 † local ~6.3GB LM Studio › copy 265 Qwen3-VL 30B-A3B Instruct Alibaba 58±1 † local ~21GB 256k LM Studio › copy 266 Qwen3-VL 8B Thinking Alibaba 58±1 local ~6.8GB 256k llama.cpp › copy 267 Qwen3 32B Alibaba 58±0 local ~20GB 131k LM Studio › copy +17 268 Qwen3 Coder 30B-A3B Instruct Alibaba 58±1 local ~20GB 160k LM Studio › copy 270 Llama 3.3 Nemotron Super 49B v1.5 NVIDIA 58±1 local ~18GB 131k llama.cpp › copy 271 Nemotron 3 Nano 30B-A3B NVIDIA 58±1 local ~20GB 262k LM Studio › copy +3 272 Ministral 3 14B Reasoning 2512 Mistral 58±1 local ~10GB 262k llama.cpp › copy 275 DeepSeek R1 0528 Qwen3 8B DeepSeek 57±1 local ~6.3GB 128k LM Studio › copy 276 Granite 4.2 3B IBM 57±1 local ~3.7GB 131k LM Studio › copy 277 Command A (03-2025) Cohere 57±1 local ~37GB 256k llama.cpp › copy 281 Qwen2.5-Omni 7B Alibaba 57±2 local ~6.4GB llama.cpp › copy 283 QED-Nano LM Provers 57±2 local ~4.1GB 262k llama.cpp › copy 284 Llama 4 Maverick (402B-A17B) Meta 57±1 local ~65GB 1M llama.cpp › copy +14 286 Qwen2.5 Coder 32B Instruct Alibaba 57±1 local ~21GB 131k LM Studio › copy +5 287 Qwen3 4B Thinking 2507 Alibaba 57±1 local ~3.9GB 262k LM Studio › copy +2 290 Athene-V2-Chat 72B Nexusflow 56±2 local ~44GB 33k LM Studio › copy 292 Sky-T1 32B Preview NovaSky (UC Berkeley) 56±5 local ~21GB LM Studio › copy 295 Qwen3-VL 4B Thinking Alibaba 56±1 local ~4.1GB 256k llama.cpp › copy 296 EXAONE Deep 32B LG AI Research 56±2 † local ~22GB 33k Ollama › copy 297 DeepSeek R1 Distill Qwen 32B DeepSeek 56±1 local ~21GB 131k LM Studio › copy +5 298 Qwen2.5-VL 72B Instruct Alibaba 56±1 local ~46GB 33k LM Studio › copy +3 299 Granite 4.1 30B IBM 56±1 † local ~19GB Ollama › copy 300 Mistral Small 3.2 24B Mistral 56±1 local ~16GB 128k LM Studio › copy +4 301 DeepSeek-V2.5 (1210) DeepSeek 56±1 local ~82GB llama.cpp › copy 302 Qwen3 8B Alibaba 56±1 local ~6.1GB 33k LM Studio › copy +14 303 DeepSeek R1 Distill Qwen 14B DeepSeek 56±1 local ~10GB 131k LM Studio › copy +2 304 Ministral 3 14B Mistral 56±1 local ~9.1GB 262k LM Studio › copy +1 305 Nemotron Nano 9B v2 NVIDIA 56±1 local ~7.6GB 131k llama.cpp › copy 309 Qwen2.5 72B Instruct Alibaba 55±1 local ~30GB 33k llama.cpp › copy +24 310 Mistral Large 2 (2411) Mistral 55±1 local ~78GB 128k llama.cpp › copy +8 311 Ministral 3 8B Reasoning 2512 Mistral 55±1 local ~6.5GB 262k LM Studio › copy 312 Magistral Small 1.0 (2506) Mistral 55±1 local ~16GB 128k LM Studio › copy 313 Qwen3 30B-A3B (Apr 2025, hybrid) Alibaba 55±1 local ~19GB 33k LM Studio › copy +10 314 Molmo 2 8B Ai2 55±2 local ~6.8GB llama.cpp › copy 317 Qwen3 4B Instruct 2507 Alibaba 55±1 local ~3.9GB 262k LM Studio › copy +4 318 Qwen2.5 Coder 14B Instruct Alibaba 55±1 local ~10GB 131k LM Studio › copy 319 Qwen3-VL 8B Instruct Alibaba 55±1 local ~6.8GB 256k llama.cpp › copy 320 Spark-X2.5 1.7B iFLYTEK (SparkLLM) 55±1 † local ~2.7GB 1M llama.cpp › copy 321 GigaChat 3.5 Ultra Instruct (432B-A28B) Sber 55±1 † local ~457GB 262k how to run › copy 322 Llama 3.1 405B Instruct Meta 55±1 local ~160GB 128k llama.cpp › copy +13 323 Qwen2.5 32B Instruct Alibaba 55±1 local ~21GB 131k LM Studio › copy +11 324 Command A Reasoning (08-2025) Cohere 55±2 local ~34GB llama.cpp › copy 325 Bielik 11B v3.0 Instruct SpeakLeash 55±2 local ~8.1GB LM Studio › copy 326 Olmo 3.1 32B Instruct Ai2 55±2 local ~21GB 66k LM Studio › copy 327 OpenThinker 32B Open Thoughts 55±1 † local ~21GB 33k LM Studio › copy 328 Magistral Small 1.1 (2507) Mistral 55±2 † local ~16GB 40k LM Studio › copy 329 EXAONE Deep 7.8B LG AI Research 55±2 † local ~6.5GB 33k llama.cpp › copy 330 Qwen2.5-Math 72B Instruct Alibaba 55±2 † local ~44GB 4k LM Studio › copy 331 OpenThinker2 32B Open Thoughts 54±1 local ~21GB 33k LM Studio › copy 332 Falcon-H1 34B Instruct TII 54±3 local ~23GB 262k llama.cpp › copy 333 Llama 3.3 70B Instruct Meta 54±1 local ~24GB 128k llama.cpp › copy +21 334 Llama 4 Scout (109B-A17B) Meta 54±1 local ~36GB 328k llama.cpp › copy +8 335 Nemotron 3 Nano 4B NVIDIA 54±1 local ~3.8GB 262k LM Studio › copy 336 Granite 4.1 8B IBM 54±1 local ~7GB 131k LM Studio › copy 337 Pixtral Large (2411) Mistral 54±3 local ~51GB llama.cpp › copy 338 Bielik 11B v2.6 Instruct SpeakLeash 54±3 local ~8.1GB LM Studio › copy 340 Mellum2 12B-A2.5B Thinking JetBrains 54±1 † local ~8.6GB 131k LM Studio › copy 341 Mistral Large 2 (2407) Mistral 54±1 local ~45GB 128k llama.cpp › copy +10 342 Mistral Small 3.1 24B (2503) Mistral 54±1 local ~17GB 128k llama.cpp › copy +7 346 Llama 3.1 Tulu 3 70B Ai2 54±1 local ~43GB 131k LM Studio › copy 347 DeepSeek-V2.5 DeepSeek 54±1 local ~151GB 164k Ollama › copy +1 348 DeepSeek-V2 Chat (0628) DeepSeek 54±1 local ~66GB llama.cpp › copy 349 GLM-4 9B Chat 1M Zhipu AI (THUDM) 53±5 local ~8.1GB 1M llama.cpp › copy 350 Mistral Small 3 24B (2501) Mistral 53±1 local ~16GB 32k LM Studio › copy +6 351 Qwen2-VL 72B Instruct Alibaba 53±1 local ~34GB llama.cpp › copy 355 Llama 3.1 Tulu 3 70B DPO Ai2 53±1 local ~22GB 131k llama.cpp › copy 357 Qwen2.5-VL 32B Instruct Alibaba 53±2 local ~22GB 33k LM Studio › copy +1 358 DeepSeek-Coder-V2 Instruct (0614) DeepSeek 53±1 local ~92GB llama.cpp › copy +2 359 s1.1 32B Simple Scaling 53±1 local ~22GB 33k LM Studio › copy 360 DeepSeek-Coder-V2 Instruct (0724) DeepSeek 53±1 local ~151GB llama.cpp › copy 361 Olmo 3 7B Think Ai2 53±1 local ~5.8GB 66k LM Studio › copy 364 Gemma 3 27B Google 53±1 local ~18GB 131k LM Studio › copy +23 365 Phi-4 14B Microsoft 53±1 local ~10GB 16k LM Studio › copy +11 366 Gemma 4 E4B Google 53±1 local ~6.9GB 131k LM Studio › copy +7 367 Ministral 3 8B Mistral 53±1 local ~6.5GB 262k LM Studio › copy +2 368 Qwen3-VL 4B Instruct Alibaba 53±1 local ~4.1GB 256k llama.cpp › copy 370 LFM2.5 2.6B Liquid AI 53±1 local ~3.2GB 131k LM Studio › copy 371 Bielik 11B v2.1 Instruct SpeakLeash 53±3 local ~8.5GB llama.cpp › copy 372 Llama 3.1 70B Instruct Meta 52±1 local ~27GB 128k llama.cpp › copy +22 374 Qwen2.5-Math 7B Instruct Alibaba 52±2 † local ~6GB 4k LM Studio › copy 375 LFM2.5 8B-A1B Liquid AI 52±1 local ~6.5GB 128k LM Studio › copy 379 Bielik 11B v2.2 Instruct SpeakLeash 52±3 local ~8.5GB llama.cpp › copy 380 Granite 4.0 H Small (32B-A9B) IBM 52±1 local ~21GB 131k LM Studio › copy +1 381 Llama 3.1 Nemotron 70B Instruct NVIDIA 52±1 local ~43GB 128k LM Studio › copy +4 384 Aya Expanse 32B Cohere 52±2 local ~22GB 128k llama.cpp › copy +1 385 Gemma 3 12B Google 52±1 local ~9.1GB 131k LM Studio › copy +10 386 Qwen2.5 Coder 7B Instruct Alibaba 52±1 local ~6GB 131k LM Studio › copy 387 Qwen2.5 14B Instruct Alibaba 52±1 local ~10GB 131k LM Studio › copy +7 388 Cogito v1 Preview Llama 8B Deep Cogito 51±5 local ~6.2GB 128k LM Studio › copy 389 Hermes 3 Llama 3.1 405B Nous Research 51±1 local ~114GB 131k llama.cpp › copy 391 OpenCoder-8B-Instruct INF (infly) 51±1 local ~6.4GB llama.cpp › copy 393 Llama 3.1 Nemotron 51B Instruct NVIDIA 51±2 local ~34GB llama.cpp › copy 394 Ministral 3 3B Reasoning 2512 Mistral 51±1 local ~3.5GB 262k LM Studio › copy 395 Qwen3 4B Alibaba 51±1 local ~3.7GB 33k LM Studio › copy +8 397 C Llama-3-Instruct-8B-SimPO-ExPO Chujie Zheng (ExPO) 51±1 local ~6.6GB llama.cpp › copy 398 LFM2 24B-A2B Liquid AI 51±1 local ~16GB 33k LM Studio › copy 399 AceReason-Nemotron-1.0-14B NVIDIA 51±2 † local ~10GB LM Studio › copy 400 Llama-3-Instruct-8B-SimPO Princeton NLP 51±1 local ~6.6GB llama.cpp › copy 401 Athene-70B Nexusflow 51±1 local ~29GB llama.cpp › copy 402 Qwen2 72B Instruct Alibaba 51±1 local ~33GB 131k llama.cpp › copy +14 403 Bielik 11B v2.0 Instruct SpeakLeash 51±3 local ~8.5GB llama.cpp › copy 404 OpenThinker3 7B Open Thoughts 50±1 local ~6GB 33k LM Studio › copy 405 CodeQwen1.5 7B Chat Alibaba 50±1 local ~6.4GB 64k llama.cpp › copy 406 Jamba 1.5 Large AI21 Labs 50±1 local ~839GB how to run › copy 408 Llama-3-8B-ProLong-512k-Instruct Princeton NLP 50±5 local ~35GB how to run › copy 409 EXAONE Deep 2.4B LG AI Research 50±2 † local ~3.2GB 33k Ollama › copy 410 Mellum2 12B-A2.5B Instruct JetBrains 50±2 † local ~8.6GB 131k LM Studio › copy 411 OpenCodeInterpreter-DS-33B M-A-P 50±1 local ~22GB LM Studio › copy 412 Llama 3.2 90B Vision Instruct Meta 50±1 local ~58GB 128k Ollama › copy +1 413 DeepSeek-Coder 33B Instruct DeepSeek 50±1 local ~21GB 16k LM Studio › copy +1 414 Yi 34B 200K (base) 01.AI 50±5 local ~23GB 200k llama.cpp › copy 415 Gemma 2 27B IT Google 50±1 local ~18GB 8k LM Studio › copy +10 416 Bielik 11B v2.3 Instruct SpeakLeash 50±2 local ~8.6GB llama.cpp › copy 417 Qwen2.5-VL 7B Instruct Alibaba 50±1 local ~6.4GB llama.cpp › copy 418 Molmo 72B (0924) Ai2 50±2 local ~309GB how to run › copy 419 Codestral 22B v0.1 Mistral AI 50±1 local ~15GB 32k LM Studio › copy 421 Llama 3 70B Instruct Meta 50±0 local ~24GB 8k llama.cpp › copy +17 422 WizardLM-2 8x22B Microsoft 50±1 local ~91GB Ollama › copy 424 WizardCoder 33B V1.1 WizardLM 50±1 local ~22GB 16k llama.cpp › copy 425 Mistral Small Instruct 22B (2409) Mistral AI 49±2 local ~15GB 32k LM Studio › copy 426 Qwen2-Math 72B Instruct Alibaba 49±1 local ~32GB 4k llama.cpp › copy 427 OLMo 2 32B Instruct (0325) Ai2 49±1 local ~21GB LM Studio › copy 428 OpenThinker2 7B Open Thoughts 49±2 † local ~6.4GB 33k llama.cpp › copy 429 Aya 23 35B Cohere For AI 49±3 local ~22GB 8k LM Studio › copy 430 Granite 4.1 3B IBM 49±1 † local ~3.7GB Ollama › copy 431 OpenCodeInterpreter-DS-6.7B M-A-P 49±1 local ~5.8GB llama.cpp › copy 432 Artigenz-Coder-DS-6.7B Artigenz 49±1 local ~5.8GB llama.cpp › copy 433 LFM2.5 1.2B Thinking Liquid AI 49±2 local ~2.2GB 33k LM Studio › copy 434 Qwen3-VL 2B Thinking Alibaba 49±1 local ~2.7GB 256k llama.cpp › copy 435 speechless-codellama-34b-v2.0 uukuguy 49±1 local ~23GB llama.cpp › copy 436 Pixtral 12B (2409) Mistral 49±2 local ~9.6GB llama.cpp › copy 438 MegaBeam-Mistral-7B-512k AWS (aws-prototyping) 49±4 local ~6.1GB llama.cpp › copy 441 AceReason-Nemotron-1.1-7B NVIDIA 49±2 † local ~6GB LM Studio › copy 442 Mixtral 8x22B Instruct v0.1 Mistral 49±1 local ~56GB 64k llama.cpp › copy +9 443 Yi-Coder 9B Chat 01.AI 49±1 local ~6.8GB 128k LM Studio › copy 444 Qwen2-Math 7B Instruct Alibaba 49±2 † local ~6GB 4k LM Studio › copy 445 Magicoder-S-DS 6.7B UIUC (ise-uiuc) 49±1 local ~5.8GB llama.cpp › copy 446 InternLM2.5 7B Chat Shanghai AI Laboratory (InternLM) 49±2 local ~6.1GB LM Studio › copy 447 Hermes 3 Llama 3.1 70B Nous Research 49±1 local ~44GB 131k Ollama › copy 448 Qwen2.5 7B Instruct Alibaba 48±1 local ~6GB 131k LM Studio › copy +12 449 DeepSeek R1 Distill Qwen 7B DeepSeek 48±1 local ~6GB 131k LM Studio › copy +6 450 XwinCoder-34B Xwin-LM 48±1 local ~23GB llama.cpp › copy 451 StarChat2 15B v0.1 Hugging Face 48±1 local ~12GB 16k llama.cpp › copy 452 Code Millenials 34B Bud Ecosystem 48±1 local ~23GB llama.cpp › copy 455 T5 Large Google 48±9 local ~4.6GB 1k how to run › copy 456 WaveCoder-Ultra-6.7B Microsoft 48±1 local ~5.8GB llama.cpp › copy 457 Phi-3.5-MoE-instruct Microsoft 48±1 local ~26GB 128k LM Studio › copy 460 Gemma 3n E4B Google 48±1 local ~6.2GB 32k llama.cpp › copy 461 Hermes 2 Theta Llama-3 70B Nous Research 48±2 local ~47GB 8k llama.cpp › copy 462 Granite 4.0 H Tiny (7B-A1B) IBM 48±1 local ~5.6GB 131k LM Studio › copy 463 DeepSeek-Coder 7B Instruct v1.5 DeepSeek 48±1 local ~5.9GB llama.cpp › copy 464 Qwen2 57B-A14B Instruct Alibaba 48±2 local ~35GB 33k LM Studio › copy 465 Qwen2.5 Coder 3B Instruct Alibaba 48±1 local ~3.3GB 33k LM Studio › copy 466 DeepSeek-Coder 6.7B Instruct DeepSeek 48±1 local ~5.8GB 16k llama.cpp › copy 467 MiniCPM3-4B OpenBMB 48±2 local ~4GB 32k LM Studio › copy 468 Bielik 4.5B v3.0 Instruct SpeakLeash 48±2 local ~4.3GB LM Studio › copy 469 Qwen3.5 2B Alibaba 47±1 local ~2.9GB 262k llama.cpp › copy +7 470 Gemma 2 9B IT Google 47±1 local ~7GB 8k LM Studio › copy +14 471 Command R Plus (08-2024) Cohere 47±1 local ~63GB 128k LM Studio › copy +1 472 GLM-4 9B Chat Zhipu AI (Z.ai) 47±2 local ~7.9GB 128k Ollama › copy +1 473 Yi-1.5 34B (base) 01.AI 47±3 local ~22GB 4k LM Studio › copy 474 Phi-4-mini-reasoning 3.8B Microsoft 47±2 local ~3.8GB 128k LM Studio › copy 475 Qwen1.5 110B Chat Alibaba 47±1 local ~45GB 32k llama.cpp › copy +1 476 WhiteRabbitNeo-33B-v1 WhiteRabbitNeo 47±1 local ~22GB llama.cpp › copy 477 DeepSeek R1 Distill Llama 8B DeepSeek 47±1 local ~6.2GB 131k LM Studio › copy +1 478 EXAONE 4.0 1.2B LG AI Research 47±2 † local ~2.2GB 66k LM Studio › copy 479 InternVL2-26B Shanghai AI Laboratory (OpenGVLab) 47±2 local ~55GB how to run › copy 480 speechless-coder-ds-6.7b uukuguy 47±1 local ~5.8GB llama.cpp › copy 481 Gemma 4 E2B Google 47±1 local ~5.1GB 131k llama.cpp › copy +6 482 Magicoder-S-CL-7B UIUC (ise-uiuc) 47±1 local ~5.8GB llama.cpp › copy 483 Aya Expanse 8B Cohere 47±2 local ~6.2GB 8k LM Studio › copy 484 Phind CodeLlama 34B v2 Phind 47±1 local ~23GB 16k Ollama › copy 486 InternLM2.5 7B Chat 1M Shanghai AI Laboratory (InternLM) 47±4 local ~6.4GB llama.cpp › copy 487 EuroLLM 9B Instruct UTTER (EuroLLM) 47±3 local ~6.9GB 4k LM Studio › copy 488 Granite 4.0 H Micro 3B IBM 47±1 local ~3.4GB 131k LM Studio › copy 491 Jamba 1.5 Mini AI21 Labs 46±1 local ~34GB llama.cpp › copy 492 MedGemma 4B IT Google 46±3 local ~4.1GB llama.cpp › copy 493 OLMo 2 13B Instruct (1124) Allen Institute for AI 46±1 local ~9.6GB 4k LM Studio › copy 494 Falcon-H1 7B Instruct TII 46±3 local ~6GB 262k LM Studio › copy 496 Cogito v1 Preview Llama 3B Deep Cogito 46±4 local ~3.4GB 128k LM Studio › copy 497 Code Llama 70B Instruct Meta 46±1 local ~28GB 16k llama.cpp › copy +1 498 Hermes 2 Pro Llama 3 8B Nous Research 46±3 local ~6.6GB 8k llama.cpp › copy 499 Llama 3 70B (base) Meta 46±2 local ~43GB LM Studio › copy 500 Granite 4.0 Micro 3B IBM 46±1 local ~3.5GB 131k LM Studio › copy 501 Command R (08-2024) Cohere 46±1 local ~21GB 128k LM Studio › copy +3 504 T5 Base Google 46±9 local ~2.4GB 1k how to run › copy 505 OpenChat 3.5 0106 OpenChat 46±1 local ~6.1GB 8k llama.cpp › copy +1 506 Qwen2-VL 7B Instruct Alibaba 46±1 local ~6.4GB LM Studio › copy 507 Qwen2.5-Math 1.5B Instruct Alibaba 46±2 † local ~2.4GB 4k LM Studio › copy 508 Yi 1.5 34B Chat 01.AI 46±1 local ~22GB 4k LM Studio › copy +5 509 DBRX Instruct Databricks 46±1 local ~85GB 32k Ollama › copy +3 510 Granite 34B Code Instruct (8K) IBM 46±1 local ~22GB Ollama › copy 511 WizardCoder Python 34B V1.0 WizardLM 46±1 local ~23GB 16k Ollama › copy 515 Granite 3.3 8B Instruct IBM 46±1 local ~6.3GB 128k LM Studio › copy 516 Tulu 2 70B Allen Institute for AI 46±2 † local ~28GB llama.cpp › copy 518 OpenChat 3.5 0106 Gemma OpenChat 46±3 local ~6.9GB 8k llama.cpp › copy 519 Olmo 3 7B Instruct Ai2 46±1 local ~5.8GB 66k LM Studio › copy 520 InternLM2.5 20B Chat Shanghai AI Laboratory (InternLM) 46±2 local ~14GB 33k llama.cpp › copy 521 StarCoder2-15B-Instruct-v0.1 BigCode 46±1 local ~11GB 16k Ollama › copy 522 Qwen1.5 72B Chat Alibaba 45±1 local ~31GB 32k llama.cpp › copy +9 523 speechless-starcoder2-15b uukuguy 45±1 local ~12GB llama.cpp › copy 524 Ministral 3 3B Mistral 45±1 local ~3.5GB 262k LM Studio › copy +2 526 OpenThinker 7B Open Thoughts 45±2 † local ~6GB 33k LM Studio › copy 527 Phi-3 Medium 128K Instruct Microsoft 45±1 local ~9.8GB 128k LM Studio › copy 528 QwQ-32B-Preview Alibaba 45±2 local ~21GB 33k LM Studio › copy +2 529 DeepSeek-Coder-V2 Lite Instruct (16B-A2.4B) DeepSeek 45±1 local ~11GB 128k LM Studio › copy +1 532 Zephyr ORPO 141B-A35B v0.1 Hugging Face 45±2 local ~56GB 66k llama.cpp › copy 533 Phi-3-medium-4k-instruct Microsoft 45±1 local ~9.8GB 4k LM Studio › copy +1 534 Qwen2-Math 1.5B Instruct Alibaba 45±2 † local ~2.4GB 4k LM Studio › copy 536 Llama 3.1 8B Instruct Meta 45±0 local ~6.2GB 128k LM Studio › copy +25 537 Command R Plus (04-2024) Cohere 45±1 local ~43GB 128k llama.cpp › copy +6 538 Mistral NeMo Instruct (2407) Mistral 44±1 local ~8.7GB 128k LM Studio › copy +9 539 LLaVA-OneVision Qwen2 72B (ov-sft) LLaVA (lmms-lab) 44±3 local ~155GB how to run › copy 540 Phi-3-mini-4k-instruct (June 2024 update) Microsoft 44±1 local ~3.7GB LM Studio › copy 541 Yi 1.5 9B Chat 01.AI 44±1 local ~6.8GB 4k LM Studio › copy +1 542 Command R7B (12-2024) Cohere 44±1 local ~6.2GB 128k LM Studio › copy 543 Qwen2-Audio 7B Instruct Alibaba 44±3 local ~6.5GB llama.cpp › copy 544 Gemma 3 4B Google 44±1 local ~3.8GB 131k LM Studio › copy +11 545 Eurus-2-7B-PRIME PRIME-RL 44±2 local ~6.4GB 4k llama.cpp › copy 546 Llama 3.1 Tulu 3 8B Ai2 44±1 local ~6.2GB 131k LM Studio › copy 547 Qwen2.5-VL 3B Instruct Alibaba 44±1 local ~3.5GB llama.cpp › copy 548 Qwen1.5 32B Chat Alibaba 44±1 local ~22GB 32k llama.cpp › copy 549 Granite 20B Code Instruct (8K) IBM 44±1 local ~14GB Ollama › copy 550 Qwen2 7B Instruct Alibaba 44±1 local ~6GB 131k LM Studio › copy +4 551 Falcon3 7B Instruct TII 44±3 local ~5.9GB 32k LM Studio › copy 552 Xwin-LM 70B v0.1 Xwin-LM 44±1 local ~28GB llama.cpp › copy 553 Qwen3-VL 2B Instruct Alibaba 44±1 local ~2.7GB 256k llama.cpp › copy 554 Dolphin 2.6 Mixtral 8x7B Cognitive Computations 44±1 local ~29GB llama.cpp › copy 555 Granite 8B Code Instruct (4K) IBM 44±1 local ~6.6GB llama.cpp › copy 556 Falcon3 10B Instruct TII 44±3 local ~7.6GB 32k LM Studio › copy 557 Code Tulu 2 34B Allen Institute for AI 44±2 † local ~72GB how to run › copy 558 Qwen3 1.7B Alibaba 44±1 local ~2.6GB 33k LM Studio › copy +10 559 Phi-4-mini 3.8B Microsoft 44±1 local ~3.8GB 128k LM Studio › copy +4 560 Ministral 8B (2410) Mistral 44±1 local ~6.2GB 128k LM Studio › copy +6 561 Granite 3.2 8B Instruct IBM 44±1 local ~6.6GB 131k llama.cpp › copy 562 Code Llama 70B Python Meta 44±1 local ~28GB 16k llama.cpp › copy 563 Llama 3.1 8B (base) Meta 44±3 local ~6.2GB LM Studio › copy 564 LFM2.5 1.2B Instruct Liquid AI 44±2 local ~2.2GB 33k LM Studio › copy 565 Granite 3.0 8B Instruct IBM 43±1 local ~6.6GB 4k llama.cpp › copy 566 Phi-3.5-mini-instruct Microsoft 43±1 local ~3.7GB 128k LM Studio › copy +4 567 Hermes 2 Theta Llama 3 8B Nous Research 43±2 local ~6.6GB 8k llama.cpp › copy 568 Yi 34B Chat 01.AI 43±1 local ~23GB 4k llama.cpp › copy +1 569 CogVLM2 Llama3 Chat 19B Zhipu AI (THUDM) 43±3 local ~43GB how to run › copy 570 Code Llama 70B (base) Meta 43±1 local ~28GB 16k llama.cpp › copy 571 Gemma 3n E2B IT Google 43±2 local ~4.7GB 32k llama.cpp › copy 573 T5 Small Google 43±9 local ~1.8GB 1k how to run › copy 574 MiniCPM-V 2.6 OpenBMB 43±2 local ~6.4GB llama.cpp › copy 575 Qwen2.5 Coder 1.5B Instruct Alibaba 43±1 local ~2.4GB 33k LM Studio › copy 576 LFM2 2.6B Liquid AI 43±2 local ~3GB 33k LM Studio › copy 577 SmolLM3 3B Hugging Face 43±1 local ~3.3GB 66k LM Studio › copy 578 Granite 3.1 8B Instruct IBM 43±1 local ~6.6GB 128k llama.cpp › copy 579 Llama 3.2 11B Vision Instruct Meta 43±2 local ~8.8GB 128k Ollama › copy 580 Qwen2.5 3B Instruct Alibaba 43±1 local ~3.3GB 33k LM Studio › copy +5 581 DeepSeek-Coder 1.3B Instruct DeepSeek 43±1 local ~2.4GB 16k Ollama › copy 582 Aya 23 8B Cohere For AI 43±3 local ~6.2GB 8k LM Studio › copy 583 Phi-3-small-8k-instruct Microsoft 43±2 local ~17GB how to run › copy 584 CodeGemma 7B IT (v1.0) Google 43±1 local ~7.1GB llama.cpp › copy 585 Aya Vision 32B Cohere 42±3 local ~71GB 16k how to run › copy 586 Tulu 2 DPO 70B Ai2 42±1 local ~32GB llama.cpp › copy +1 587 Mathstral 7B v0.1 Mistral AI 42±1 local ~5.8GB 32k LM Studio › copy 588 Yi-1.5 9B (base) 01.AI 42±2 local ~6.8GB 4k LM Studio › copy 590 Llama 3 8B Instruct Meta 42±0 local ~6.6GB 8k llama.cpp › copy +19 591 WizardLM 70B V1.0 Microsoft 42±1 local ~32GB llama.cpp › copy 592 WizardCoder Python 13B V1.0 WizardLM 42±2 local ~9.8GB 16k llama.cpp › copy 593 Hermes 3 Llama 3.1 8B Nous Research 42±1 local ~6.6GB 128k llama.cpp › copy 594 Falcon2 11B (base) TII 42±3 local ~8.2GB 8k Ollama › copy 595 Granite 34B Code Base (8K) IBM 42±1 local ~24GB llama.cpp › copy 596 speechless-starcoder2-7b uukuguy 42±1 local ~6.1GB llama.cpp › copy 597 Command R (03-2024) Cohere 42±1 local ~24GB 128k llama.cpp › copy +6 599 OLMo 2 7B Instruct (1124) Allen Institute for AI 42±1 local ~5.8GB 4k LM Studio › copy 600 WizardCoder-15B-V1.0 WizardLM 42±1 local ~12GB llama.cpp › copy 601 Snowflake Arctic Instruct Snowflake 41±2 local ~1007GB how to run › copy 602 Phi-3-vision-128k-instruct Microsoft 41±2 local ~10GB how to run › copy 603 OpenChat 3.5 OpenChat 41±2 local ~6.1GB 8k llama.cpp › copy 604 InternVL2-4B Shanghai AI Laboratory (OpenGVLab) 41±2 local ~10GB how to run › copy 605 Qwen1.5 14B Chat Alibaba 41±1 local ~11GB 32k Ollama › copy +3 606 Code Llama 34B Python Meta 41±1 local ~23GB 16k Ollama › copy 607 speechless-coding-7b-16k-tora uukuguy 41±1 local ~16GB how to run › copy 608 DeepSeek-Coder 33B Base DeepSeek 41±1 local ~22GB 16k llama.cpp › copy 609 InternLM2 Chat 20B Shanghai AI Laboratory (InternLM) 41±1 local ~14GB llama.cpp › copy 610 DeepSeek LLM 67B Chat DeepSeek 41±1 local ~31GB 4k llama.cpp › copy 611 Llama 2 70B (base) Meta 41±1 local ~32GB 4k llama.cpp › copy 612 Mixtral 8x7B v0.1 (base) Mistral AI 41±1 local ~29GB 32k llama.cpp › copy 613 North Micro Vision Instruct (2.4B) Cohere 41±2 † local ~3.8GB 128k how to run › copy 614 CodeQwen1.5 7B (base) Alibaba 41±1 local ~6.4GB 66k llama.cpp › copy 615 Granite 4.0 1B IBM 41±1 local ~2.4GB 128k LM Studio › copy 616 Mixtral 8x7B Instruct v0.1 Mistral 41±1 local ~29GB 32k LM Studio › copy +15 617 Molmo 7B-D (0924) Ai2 41±1 local ~35GB how to run › copy 618 A OpenHermes-2.5-Code-290k-13B ajibawa-2023 41±1 local ~9.8GB llama.cpp › copy 619 Granite 4.0 H 1B IBM 40±1 local ~2.3GB 131k LM Studio › copy 620 Llama3-OpenBioLLM-8B Saama AI Labs 40±2 local ~6.6GB llama.cpp › copy 621 Nous Hermes 2 Mistral 7B DPO Nous Research 40±2 local ~6.1GB 33k llama.cpp › copy 622 Nous Hermes 2 Mixtral 8x7B DPO Nous Research 40±2 local ~31GB 33k llama.cpp › copy 623 Deita 7B v1.0 HKUST NLP 40±2 local ~32GB how to run › copy 624 Code Llama 34B Instruct Meta 40±1 local ~22GB 16k LM Studio › copy +1 625 Code Llama 34B (base) Meta 40±1 local ~23GB 16k Ollama › copy +1 626 Starling-LM 7B beta Nexusflow 40±1 local ~6GB 8k LM Studio › copy +3 627 LFM2 1.2B Liquid AI 40±2 local ~2.2GB 33k LM Studio › copy 628 Code Tulu 2 13B Allen Institute for AI 40±2 † local ~29GB how to run › copy 629 LLaVA-v1.6-34B LLaVA 40±2 local ~24GB 4k Ollama › copy 630 Bielik 1.5B v3.0 Instruct SpeakLeash 40±3 local ~2.4GB LM Studio › copy 631 OpenHermes 2.5 Mistral 7B Nous Research 39±1 local ~6.1GB llama.cpp › copy +2 632 Granite 3.3 2B Instruct IBM 39±1 † local ~3GB 128k LM Studio › copy 633 Phi-3-mini-128k-instruct (Apr 2024) Microsoft 39±2 local ~9.5GB how to run › copy +1 634 Mistral 7B Instruct v0.3 Mistral 39±1 local ~5.8GB 32k LM Studio › copy +4 635 Vicuna 33B v1.3 LMSYS 39±1 local ~23GB 2k Ollama › copy +2 636 DeepSeek-Coder 6.7B Base DeepSeek 39±1 local ~5.8GB 16k llama.cpp › copy 637 Starling-LM 7B alpha UC Berkeley (NEST) 39±1 local ~6.1GB 8k llama.cpp › copy +2 638 Granite 8B Code Base (4K) IBM 39±1 local ~6.6GB llama.cpp › copy 639 StarCoder2 15B BigCode 39±1 local ~11GB 16k LM Studio › copy 640 speechless-code-mistral-7b-v1.0 uukuguy 39±1 local ~17GB how to run › copy 641 Falcon-H1 3B Instruct TII 39±4 local ~3.4GB 131k LM Studio › copy 642 Phi-2 (2.7B) Microsoft 39±1 local ~3.2GB 2k LM Studio › copy +2 643 Granite 3.0 2B Instruct IBM 39±1 local ~3.2GB 4k llama.cpp › copy 644 Llama 2 70B Chat Meta 39±1 local ~32GB 4k llama.cpp › copy +10 645 Code Llama 13B Instruct Meta 39±1 local ~9.8GB 16k llama.cpp › copy 646 MistralHermes-CodePro-7B-v1 beowolx 39±1 local ~6.1GB llama.cpp › copy 647 Llama-3-Instruct-8B-SimPO-v0.2 Princeton NLP 39±1 local ~6.6GB llama.cpp › copy 648 Llama 3.2 3B Instruct Meta 38±1 local ~3.4GB 131k LM Studio › copy +11 649 Qwen-14B-Chat Alibaba 38±1 local ~11GB llama.cpp › copy 650 Falcon-180B-Chat TII 38±2 local ~115GB 2k Ollama › copy 651 CodeGemma 7B (v1.0) Google 38±1 local ~7.1GB llama.cpp › copy 652 Code Llama 13B Python Meta 38±1 local ~9.8GB 16k llama.cpp › copy 653 Tulu 2 13B Allen Institute for AI 38±2 local ~9.8GB llama.cpp › copy 654 Phi-3-mini-4k-instruct (Apr 2024) Microsoft 38±2 local ~4GB llama.cpp › copy 655 Apertus 8B Instruct (2509) Swiss AI 38±4 local ~6.3GB 66k LM Studio › copy 657 Granite 3B Code Instruct (2K) IBM 38±2 local ~3.7GB llama.cpp › copy 658 DeepSeek-V2 Lite Chat (16B-A2.4B) DeepSeek 38±1 local ~11GB 32k LM Studio › copy 659 BioMistral-7B BioMistral 38±3 local ~6.1GB llama.cpp › copy 660 Qwen3.5 0.8B Alibaba 38±1 local ~2GB 262k llama.cpp › copy +2 661 Code Tulu 2 7B Allen Institute for AI 38±2 † local ~16GB how to run › copy 662 SOLAR 10.7B Instruct v1.0 Upstage 37±1 local ~8.3GB 4k llama.cpp › copy +2 663 Phi-3.5-vision-instruct Microsoft 37±2 local ~10GB how to run › copy 664 Tulu 2 DPO 13B Allen Institute for AI 37±1 local ~9.8GB llama.cpp › copy 665 Yi-1.5 6B (base) 01.AI 37±3 local ~5.1GB 4k LM Studio › copy 666 Qwen2-VL 2B Instruct Alibaba 37±1 local ~2.8GB 33k LM Studio › copy 667 DeepSeek R1 Distill Qwen 1.5B DeepSeek 37±2 local ~2.6GB 131k LM Studio › copy +1 668 Gemma 2 2B IT Google 37±1 local ~3.1GB 8k LM Studio › copy +4 669 Qwen2.5 Coder 0.5B Instruct Alibaba 37±1 local ~1.8GB 33k LM Studio › copy 670 Granite 20B Code Base (8K) IBM 37±1 local ~15GB llama.cpp › copy 671 Gemma 1.1 7B IT Google 37±1 local ~7.1GB 8k llama.cpp › copy +2 672 Code Llama 7B Python Meta 37±1 local ~5.8GB 16k llama.cpp › copy 673 Dolphin 2.2.1 Mistral 7B Cognitive Computations 37±2 local ~6.1GB llama.cpp › copy 674 Code Llama 13B (base) Meta 37±1 local ~9.2GB 16k LM Studio › copy +1 675 Qwen1.5 7B Chat Alibaba 37±1 local ~6.5GB 32k llama.cpp › copy +4 676 Yi 1.5 6B Chat 01.AI 37±2 local ~5.1GB 4k LM Studio › copy 677 Falcon3 3B Instruct TII 37±3 local ~3.4GB 32k LM Studio › copy 678 Zephyr 7B alpha Hugging Face 36±1 local ~6.1GB llama.cpp › copy 679 Vicuna 13B v1.5 LMSYS 36±2 local ~9.8GB 4k llama.cpp › copy 680 Granite 3.1 2B Instruct IBM 36±1 local ~3.1GB 128k llama.cpp › copy 681 EXAONE 3.5 2.4B Instruct LG AI Research 36±2 local ~3GB 33k LM Studio › copy 683 Code Llama 7B Instruct Meta 36±1 local ~5.5GB 16k LM Studio › copy 684 LFM2 700M Liquid AI 36±2 local ~1.9GB 33k LM Studio › copy 685 Granite 3.2 2B Instruct IBM 36±1 local ~3GB 131k LM Studio › copy 686 Mistral 7B Instruct v0.2 Mistral 36±1 local ~6GB 32k LM Studio › copy +9 687 WizardLM 13B V1.2 Microsoft 36±1 local ~9.8GB llama.cpp › copy 688 Tulu 2 7B Allen Institute for AI 36±2 local ~5.8GB llama.cpp › copy 689 xDAN-L1-Chat-RL-v1 xDAN-AI 36±1 local ~6.1GB llama.cpp › copy 690 Llama 3 8B (base) Meta 36±1 local ~6.6GB llama.cpp › copy 691 Mistral 7B v0.1 (base) Mistral AI 36±0 local ~5.8GB 8k LM Studio › copy +4 692 Qwen2.5 1.5B Instruct Alibaba 36±1 local ~2.4GB 33k LM Studio › copy +6 694 Gemma 7B (base) Google 35±1 local ~7.1GB 8k llama.cpp › copy +3 695 Tulu 2 DPO 7B Allen Institute for AI 35±1 local ~5.8GB llama.cpp › copy 696 Eurus-2-7B-SFT PRIME-RL 35±3 † local ~6.4GB llama.cpp › copy 697 Falcon 40B (base) TII 35±1 local ~27GB 2k Ollama › copy 698 StarCoder2 7B BigCode 35±1 local ~6.1GB 16k LM Studio › copy 699 Granite 3.0 3B-A800M Instruct IBM 35±1 local ~3.7GB 4k llama.cpp › copy 700 DeepSeek LLM 7B Chat DeepSeek 35±2 † local ~5.7GB Ollama › copy 701 StarCoder 15.5B BigCode 35±1 local ~11GB Ollama › copy 702 Granite 3.1 3B-A800M Instruct IBM 35±2 † local ~3.6GB 131k llama.cpp › copy 703 Llama 2 13B (base) Meta 34±1 local ~9.3GB 4k Ollama › copy +3 704 Code Llama 7B (base) Meta 34±1 local ~5.5GB 16k LM Studio › copy +2 705 Nous-Hermes-13b Nous Research 34±2 local ~9.8GB 2k llama.cpp › copy 706 ChatGLM3 6B 128K Zhipu AI (THUDM) 34±4 local ~5.8GB 131k llama.cpp › copy 707 Zephyr 7B beta Hugging Face 34±1 local ~6.1GB llama.cpp › copy +3 709 Qwen3 0.6B Alibaba 33±1 local ~1.8GB 33k LM Studio › copy +4 710 Llama 2 13B Chat Meta 33±1 local ~9.8GB 4k llama.cpp › copy +9 711 Flan-T5 XXL Google 33±1 local ~49GB how to run › copy 712 StarCoder2 3B BigCode 33±1 local ~3.4GB 16k llama.cpp › copy 713 Granite 3B Code Base (2K) IBM 33±1 local ~3.7GB llama.cpp › copy 715 StarCoderBase 15.5B BigCode 33±1 local ~12GB llama.cpp › copy 716 Vicuna 7B v1.5 LMSYS 33±1 local ~5.8GB 4k llama.cpp › copy +1 717 Guanaco 33B University of Washington 33±2 local ~70GB how to run › copy 718 Stable Code 3B Stability AI 33±1 local ~3.3GB 16k llama.cpp › copy 719 OLMo 2 1B Instruct (0425) Allen Institute for AI 33±2 local ~2.4GB 4k llama.cpp › copy 720 DeepSeek-Coder 1.3B Base DeepSeek 32±1 local ~2.4GB 16k Ollama › copy 721 Orca 2 13B Microsoft 32±2 local ~9.8GB 4k llama.cpp › copy 722 Gemma 7B IT Google 32±1 local ~7.1GB 8k llama.cpp › copy +5 723 Mistral 7B Instruct v0.1 Mistral 32±1 local ~6.1GB 8k llama.cpp › copy +2 724 Qwen1.5 4B Chat Alibaba 32±2 local ~4.1GB 32k llama.cpp › copy 725 Ghost 7B Alpha Ghost X 32±2 local ~6.1GB llama.cpp › copy 726 CodeGemma 2B (v1.0) Google 32±1 local ~3.2GB llama.cpp › copy 727 Qwen-7B (base) Alibaba 32±1 local ~6.6GB 33k llama.cpp › copy 728 Phi-1.5 (1.3B) Microsoft 32±1 local ~2.4GB 2k llama.cpp › copy 729 Falcon-H1 1.5B Instruct TII 31±4 local ~2.4GB 131k LM Studio › copy 730 Flan-T5 XL Google 31±2 local ~14GB how to run › copy 731 Qwen2 1.5B Instruct Alibaba 31±1 local ~2.4GB 32k LM Studio › copy +1 732 Qwen-7B-Chat Alibaba 31±1 local ~6.6GB 33k llama.cpp › copy 733 Gemma 3 1B Google 31±1 local ~2.2GB 32k LM Studio › copy +7 734 StarCoderBase 7B BigCode 31±1 local ~6GB Ollama › copy 735 Llama 2 7B (base) Meta 31±1 local ~5.5GB 4k Ollama › copy +5 736 OPT-66B Meta 31±1 local ~141GB 2k how to run › copy 737 LFM2 350M Liquid AI 30±2 local ~1.7GB 33k LM Studio › copy 738 SmolLM2 1.7B Instruct Hugging Face 30±1 local ~2.6GB 8k LM Studio › copy 739 Llama 3.2 1B Instruct Meta 30±1 local ~2.2GB 131k LM Studio › copy +13 740 Falcon 7B (base) TII 30±1 local ~5.9GB 2k Ollama › copy +1 741 Llama 2 7B Chat Meta 30±1 local ~5.8GB 4k llama.cpp › copy +11 742 Baichuan2-7B-Base Baichuan 30±1 local ~17GB how to run › copy 745 OLMo 7B Instruct Ai2 29±2 local ~16GB how to run › copy 746 StableLM-3B-4E1T Stability AI 29±1 local ~3.3GB 4k llama.cpp › copy 747 Gemma 2B (base) Google 29±1 local ~3.2GB 8k llama.cpp › copy +3 748 OpenLLaMA 7B v2 OpenLM Research 29±1 local ~9.1GB llama.cpp › copy 749 Gemma 1.1 2B IT Google 29±1 local ~3.2GB 8k llama.cpp › copy +1 750 StableLM-Base-Alpha 7B v2 Stability AI 29±1 local ~30GB 4k how to run › copy 751 Granite 3.1 1B-A400M Instruct IBM 29±2 † local ~2.3GB 131k llama.cpp › copy 752 OPT-30B Meta 29±1 local ~64GB 2k how to run › copy 753 NexusRaven V2 13B Nexusflow 29±3 local ~9.3GB 16k Ollama › copy 754 OLMo 7B Allen Institute for AI 28±1 † local ~30GB 2k how to run › copy 755 Falcon 40B Instruct TII 28±2 local ~27GB Ollama › copy 756 GPT-NeoX-20B EleutherAI 28±1 local ~14GB 2k LM Studio › copy 759 StarCoderBase 3B BigCode 28±1 local ~3.4GB Ollama › copy 760 Granite 3.0 1B-A400M Instruct IBM 27±1 local ~2.3GB 4k llama.cpp › copy 761 RedPajama-INCITE 7B Base Together 27±1 local ~16GB 2k how to run › copy 762 ChatGLM3-6B Zhipu AI (THUDM) 27±2 local ~5.8GB llama.cpp › copy 763 Granite 4.0 H 350M IBM 27±1 † local ~1.7GB 33k LM Studio › copy 764 Flan-T5 Large Google 27±2 local ~4.8GB how to run › copy 766 Gemma 2B IT Google 27±1 local ~3.1GB 8k llama.cpp › copy +3 767 EuroLLM 1.7B Instruct UTTER (EuroLLM) 27±3 local ~2.4GB 4k LM Studio › copy 768 Qwen2.5 0.5B Instruct Alibaba 27±2 local ~1.8GB 33k LM Studio › copy +1 770 GPT4All-13B-Snoozy Nomic AI 26±2 local ~56GB how to run › copy 771 OPT-13B (13 billion parameters) Meta 26±1 local ~29GB 2k how to run › copy 772 Granite 4.0 350M IBM 26±1 local ~1.7GB 32k LM Studio › copy 775 Falcon 7B Instruct TII 25±2 local ~5.9GB Ollama › copy 776 Qwen2 0.5B Instruct Alibaba 25±2 local ~1.8GB 32k LM Studio › copy 777 Pythia 12B EleutherAI 25±1 local ~9.5GB 2k llama.cpp › copy 778 RedPajama-INCITE Base 3B v1 Together 25±3 local ~3.4GB 2k llama.cpp › copy 779 ChatGLM2-6B Zhipu AI (THUDM) 25±2 local ~15GB how to run › copy 780 GPT-J 6B EleutherAI 25±1 local ~14GB 2k how to run › copy 781 OpenLLaMA 3B v2 OpenLM Research 25±1 local ~4.2GB llama.cpp › copy 782 OPT-6.7B Meta 24±1 local ~16GB 2k how to run › copy 784 Falcon3 1B Instruct TII 24±4 local ~2.4GB 8k LM Studio › copy 785 StableLM-Base-Alpha 3B v2 Stability AI 24±1 local ~13GB 4k how to run › copy 786 Qwen1.5 1.8B Chat Alibaba 24±2 local ~2.7GB 33k Ollama › copy 787 Pythia 6.9B EleutherAI 23±1 local ~6.1GB 2k llama.cpp › copy 788 OpenAssistant SFT-4 Pythia 12B LAION (OpenAssistant) 22±1 local ~9.5GB llama.cpp › copy 789 Pythia 2.8B EleutherAI 21±1 local ~3.4GB 2k llama.cpp › copy 790 BLOOM 7.1B BigScience 21±1 local ~7.1GB 2k llama.cpp › copy 791 OLMo 1B Allen Institute for AI 21±2 † local ~2.2GB 2k llama.cpp › copy 792 Phi-1 (1.3B) Microsoft 21±4 local ~2.4GB 2k llama.cpp › copy 793 Qwen1.5 0.5B Chat Alibaba 21±3 local ~1.8GB 33k LM Studio › copy 794 ChatGLM-6B Zhipu AI (THUDM) 20±2 local ~16GB how to run › copy 795 Pythia 2.8B (deduped) EleutherAI 20±1 local ~3.4GB 2k llama.cpp › copy 796 Flan-T5 Base Google 20±3 † local ~2.5GB how to run › copy 797 Falcon-RW 1B TII 20±2 local ~4.3GB 2k how to run › copy 798 OPT-2.7B Meta 19±1 local ~7.1GB 2k how to run › copy 799 SmolLM2 360M Instruct Hugging Face 19±3 local ~1.7GB 8k LM Studio › copy 800 GPT-Neo 2.7B EleutherAI 18±1 local ~13GB 2k how to run › copy +1 802 Pythia 1.4B EleutherAI 18±2 local ~2.4GB 2k llama.cpp › copy 803 BLOOM 3B BigScience 18±1 local ~4GB 2k llama.cpp › copy 804 FastChat-T5 3B LMSYS 17±2 local ~8.5GB how to run › copy 806 OPT-1.3B Meta 16±1 local ~4.3GB 2k how to run › copy 807 Gemma 3 270M IT Google 15±4 local ~1.7GB 32k LM Studio › copy 808 Pythia 1B EleutherAI 14±1 local ~2.2GB 2k llama.cpp › copy 809 StableLM-Tuned-Alpha 7B Stability AI 14±2 local ~6.9GB llama.cpp › copy 810 BLOOM 1.7B BigScience 14±1 local ~3.1GB 2k llama.cpp › copy 811 Flan-T5 Small Google 14±3 † local ~1.8GB how to run › copy 812 GPT-Neo 1.3B EleutherAI 14±2 local ~7.1GB 2k how to run › copy 813 GPT-2 XL (1.5B) OpenAI 11±1 local ~2.8GB 1k llama.cpp › copy +2 814 BLOOM 1.1B BigScience 11±1 local ~2.6GB 2k llama.cpp › copy 815 Pythia 410M EleutherAI 10±2 local ~1.8GB 2k llama.cpp › copy 817 StableLM-Base-Alpha 7B Stability AI 9±1 local ~35GB 4k how to run › copy 818 Zyte-1B venkycs (aihub-app) 8±2 local ~2.2GB llama.cpp › copy 819 GPT-Neo 125M EleutherAI 5±5 local ~2.1GB 2k how to run › copy 820 BLOOM 560M BigScience 5±2 local ~2.1GB 2k llama.cpp › copy 821 OPT-350M Meta 5±2 local ~2.2GB 2k how to run › copy 822 StableLM-Base-Alpha 3B Stability AI 4±1 local ~17GB 4k how to run › copy 823 Pythia 160M EleutherAI 3±2 local ~1.6GB 2k llama.cpp › copy 824 OPT-125M Meta 3±2 local ~1.8GB 2k how to run › copy 825 GPT-2 Large (774M) OpenAI 1±2 local ~2GB 1k llama.cpp › copy 826 GPT-2 Medium (355M) OpenAI -1±2 local ~1.8GB 1k llama.cpp › copy 827 Pythia 70M EleutherAI -7±2 local ~1.6GB 2k llama.cpp › copy 828 GPT-2 Small (124M) OpenAI -9±3 local ~1.6GB 1k LM Studio › copy — K2 Horizon 7B Institute of Foundation Models (MBZUAI) not scored yet local ~7.7GB 524k llama.cpp › copy 
