whatmodel.sh · find the best AI models you can run

Best AI models for images and documents to run locally

A leaderboard of the best AI models for images and documents you can run on your own computer. Qwen3.8 Max (2.4T-A95B) is #1 right now, followed by Qwen3.8-Flash-Next and GLM-5.3-Flash. Models are ranked on tests that ask questions about images, charts and documents, like MMMU and CharXiv. Each model shows the download that fits and the command to run it.

83 models · scores combine 47 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][agent tasks][coding][chat & writing][math][vision & documents][web search]

Scores use reviewed vision & documents evaluations only. Compare scores within this task. Models without task measurements are excluded.

Filter by your hardware and budget · local only · reset
+ more
set[all sets][Arena vision (style controlled) · 199][CharXiv descriptive questions · 2]

Filter the model list while keeping task scores. Models without a shared score scale are not yet calibrated; select a set to see its own scores.

Detect your exact chip or graphics card:

curl -G whatmodel.sh/ -d max=0 --data-urlencode "mac=$(sysctl -n hw.memsize machdep.cpu.brand_string)"Mac

curl -G whatmodel.sh/ -d max=0 --data-urlencode "ram=$(awk '/MemT/{print $2}' /proc/meminfo)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null)"Linux

curl.exe -G whatmodel.sh/ -d max=0 --data-urlencode "ram=$((gcim Win32_ComputerSystem).TotalPhysicalMemory)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>$null)"Windows

$ terminal

detecting your OS…

Run curl "whatmodel.sh/?max=0"to get this list in your terminal (add &format=json for agents).

ram[8][16][24][32][48][64][96][128][192][256]GB
gpu[apple silicon][graphics card][none]
price[local][$0.05][$0.25][$1][$5][$20][any]max per M

detecting your OS…

Score vs memory to run

#modeltask score↓where↓speed↓RAM↓context↓get itsources
#modeltask score↓where↓speed↓RAM↓context↓get itsources
2Qwen3.8 Max (2.4T-A95B) Alibaba71±2*local~380GB262kllama.cpp › LMArena leaderboard datasetQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
10Qwen3.8-Flash-Next Alibaba69±4*local~59GB262kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
25GLM-5.3-Flash Z.ai67±2*local~103GB1Mllama.cpp › LMArena leaderboard datasetHow Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
26Kimi K3 Moonshot AI67±6*†local~884GB1Mllama.cpp › Moonshot AI vendor-reported benchmark scores for its own Kimi models (Hugging Face model cards)
39Qwen3.5 397B-A17B Alibaba65±2local~65GB262kllama.cpp › LMArena leaderboard datasetQwen/Qwen3.5-397B-A17B model cardQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams (arXiv:2608.12262v1)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
40Kimi K2.6 Moonshot AI64±2local~317GB262kllama.cpp › LMArena leaderboard datasetMoonshot AI vendor-reported benchmark scores for its own Kimi models (Hugging Face model cards)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
42Qwen3.8 27B Alibaba64±2local~18GB262kLM Studio › LMArena leaderboard datasetQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Qwen/Qwen3.8-27B model cardSciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding (arXiv:2609.05141v2)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
47Kimi K2.5 Moonshot AI63±2local~160GB262kllama.cpp › LMArena leaderboard datasetSciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding (arXiv:2609.05141v2)Qwen/Qwen3.5-397B-A17B model cardChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)Moonshot AI vendor-reported benchmark scores for its own Kimi models (Hugging Face model cards)Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams (arXiv:2608.12262v1)
51MiMo-V2.6-Flash (309B-A15B) Xiaomi62±2*local~136GB1Mllama.cpp › LMArena leaderboard dataset
52Gemma 4 31B Google62±2local~21GB262kLM Studio › LMArena leaderboard datasetGemma Team — Gemma 4 Technical Reportmeta-models/Muse-Glimmer-30B model card (speed and benchmark tables)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)
53Qwen3.6 27B Alibaba62±2local~18GB262kLM Studio › Qwen/Qwen3.6-27B model cardQwen/Qwen3.8-27B model cardmeta-models/Muse-Glimmer-30B model card (speed and benchmark tables)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
55MiMo-V2.6-Pro Xiaomi62±2*local~443GB1Mllama.cpp › LMArena leaderboard dataset
56Qwen3.5 35B-A3B Alibaba61±2local~23GB262kLM Studio › Qwen/Qwen3.5-122B-A10B model cardQwen/Qwen3.6-35B-A3B model cardChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)Qwen/Qwen3.5-27B model cardHow Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
58Qwen3.5 122B-A10B Alibaba61±2local~75GB262kLM Studio › Qwen/Qwen3.5-122B-A10B model cardLMArena leaderboard datasetQwen/Qwen3.5-27B model cardHow Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
60Qwen3.6 35B-A3B Alibaba61±3local~23GB262kLM Studio › Qwen/Qwen3.6-27B model cardQwen/Qwen3.6-35B-A3B model cardHow Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
61Gemma 4 26B-A4B Google61±2local~18GB262kLM Studio › LMArena leaderboard datasetGemma Team — Gemma 4 Technical Reportgoogle/diffusiongemma-26B-A4B-it model card
64Qwen3.5 27B Alibaba60±1local~18GB262kLM Studio › Qwen/Qwen3.5-122B-A10B model cardLMArena leaderboard datasetQwen/Qwen3.6-35B-A3B model cardQwen/Qwen3.5-27B model cardSpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models (arXiv:2610.12402v1)BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)+1
65MiniMax-M3 MiniMax60±2local~137GB1Mllama.cpp › LMArena leaderboard datasetHow Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
68Muse Glimmer 30B Meta60±4†local~19GB131kllama.cpp › meta-models/Muse-Glimmer-30B model card (speed and benchmark tables)
69MiMo-V2.5 (310B-A15B) Xiaomi60±2local~100GB1Mllama.cpp › LMArena leaderboard datasetSciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding (arXiv:2609.05141v2)XiaomiMiMo/MiMo-V2.5 model cardXiaomi MiMo vendor-reported benchmark scores for its own models (mimo.xiaomi.com launch pages)
72Inkling (975B-A41B) Thinking Machines59±5*†local~156GB1Mllama.cpp › thinkingmachines/Inkling-Small model card
78Qwen3.5 9B Alibaba57±2local~7.4GB262kllama.cpp › Qwen/Qwen3.5-9B model cardChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)Qwen/Qwen3.5-4B model cardBEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models (arXiv:2610.12402v1)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
79Inkling Small (266B-A12B) Thinking Machines56±2local~86GB1Mllama.cpp › LMArena leaderboard datasetthinkingmachines/Inkling-Small model card
80Gemma 4 12B Google56±4†local~8.5GB262kLM Studio › Gemma Team — Gemma 4 Technical Report
86Qwen3-VL 235B-A22B Instruct Alibaba55±1local~134GB256kLM Studio › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)LMArena leaderboard datasetChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)
87Mistral Medium 3.5 (128B) Mistral55±2*local~42GB262kllama.cpp › LMArena leaderboard dataset
92Qwen3-VL 235B-A22B Thinking Alibaba54±2local~111GB256kLM Studio › LMArena leaderboard datasetQwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)Qwen/Qwen3.5-397B-A17B model card
94Mistral Large 3 (675B-A41B) Mistral54±2*local~108GB262kllama.cpp › LMArena leaderboard datasetmistralai/Mistral-Small-4-119B-2603 model card
96Qwen3-VL 32B Thinking Alibaba54±2†local~22GB256kLM Studio › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
97Qwen3.5 4B Alibaba53±2local~4.3GB262kllama.cpp › Qwen/Qwen3.5-9B model cardChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)Qwen/Qwen3.5-4B model cardBEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models (arXiv:2610.12402v1)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
101Qwen3-VL 32B Instruct Alibaba52±2†local~22GB256kLM Studio › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
103Mistral Small 4 (119B-A6.5B) Mistral52±7*†local~40GB262kllama.cpp › mistralai/Mistral-Small-4-119B-2603 model card
106GLM-4.6V Z.ai51±2local~51GB128kllama.cpp › LMArena leaderboard datasetZ.ai GLM-V GitHub repository benchmark image (GLM-4.6V)SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding (arXiv:2609.05141v2)
107Apriel 1.6 15B Thinker ServiceNow50±4*†local~10GBLM Studio › ServiceNow-AI/Apriel-1.6-15b-Thinker model card
108GLM-4.5V Z.ai50±2local~69GB64kllama.cpp › LMArena leaderboard datasetZ.ai GLM-V GitHub repository benchmark image (GLM-4.6V)ServiceNow-AI/Apriel-1.6-15b-Thinker model cardChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)
110Qwen3-VL 30B-A3B Thinking Alibaba49±2†local~21GB256kLM Studio › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
115Qwen3-VL 8B Thinking Alibaba47±2local~6.8GB256kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)
116Llama 4 Maverick (402B-A17B) Meta47±2local~65GB1Mllama.cpp › LMArena leaderboard datasetApriel-1.5-15b-Thinker (arXiv:2510.01141v1), Table 4 multimodal benchmarksVMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark (arXiv:2508.13680v5)
119Qwen3-VL 30B-A3B Instruct Alibaba46±2†local~21GB256kLM Studio › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
120Magistral Small 1.2 Mistral46±5*local~16GB131kLM Studio › Apriel-1.5-15b-Thinker (arXiv:2510.01141v1), Table 4 multimodal benchmarks
124Llama 4 Scout (109B-A17B) Meta45±2*local~36GB328kllama.cpp › LMArena leaderboard datasetVMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark (arXiv:2508.13680v5)
125Mistral Small 3.2 24B Mistral44±2local~16GB128kLM Studio › LMArena leaderboard datasetVMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark (arXiv:2508.13680v5)mistralai/Mistral-Small-3.2-24B-Instruct-2506 model cardmistralai/Mistral-Small-4-119B-2603 model card
126Qwen3-VL 4B Thinking Alibaba44±2local~4.1GB256kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)
128Qwen2.5-VL 72B Instruct Alibaba44±1local~46GB33kLM Studio › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)LMArena leaderboard datasetQwen2.5-VL-32B-Instruct model cardChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark (arXiv:2508.13680v5)Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation (arXiv:2504.07072v2)+2
129Qwen3-VL 8B Instruct Alibaba44±2local~6.8GB256kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
131Mistral Small 3.1 24B (2503) Mistral44±2local~17GB128kllama.cpp › LMArena leaderboard datasetMistral AI vendor-reported benchmark scores for its own models (Hugging Face model cards)mistralai/Mistral-Small-3.2-24B-Instruct-2506 model card
133Gemma 3 27B Google42±2local~18GB131kLM Studio › LMArena leaderboard datasetGemma Team — Gemma 4 Technical ReportGoogle DeepMind Gemma 3 270M IT model cardVisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback? (arXiv:2608.10408v1)VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark (arXiv:2508.13680v5)Gemma Team — Gemma 3 Technical Report
135Molmo 2 8B Ai242±2local~6.8GBllama.cpp › LMArena leaderboard datasetMolmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding (Ai2, arXiv 2601.10611v4)
136Qwen2.5-VL 32B Instruct Alibaba42±2local~22GB33kLM Studio › LMArena leaderboard datasetQwen2.5-VL-32B-Instruct model cardApriel-1.5-15b-Thinker (arXiv:2510.01141v1), Table 4 multimodal benchmarksChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation (arXiv:2504.07072v2)VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark (arXiv:2508.13680v5)
138Gemma 4 E4B Google40±4†local~6.9GB131kLM Studio › Gemma Team — Gemma 4 Technical Report
139Pixtral Large (2411) Mistral40±2local~51GBllama.cpp › LMArena leaderboard datasetMistral AI vendor-reported benchmark scores for its own models (Hugging Face model cards)
140Qwen3-VL 4B Instruct Alibaba40±2local~4.1GB256kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
141Qwen3.5 2B Alibaba39±2local~2.9GB262kllama.cpp › Qwen/Qwen3.5-2B model cardCohereLabs/North-Micro-Vision-Instruct model card (benchmark table)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models (arXiv:2610.12402v1)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
143Qwen2-VL 72B Instruct Alibaba38±1local~34GBllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)LMArena leaderboard datasetPixtral 12B (Mistral AI, arXiv 2410.07073v2)Qwen2.5-VL-32B-Instruct model cardCapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)Ai2 Molmo-72B-0924 model card: Human Preference Elo Rating column
148Qwen2.5-VL 7B Instruct Alibaba35±2local~6.4GBllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)
150Qwen3-VL 2B Thinking Alibaba34±2local~2.7GB256kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)
151DeepSeek V4 Flash Vision (Exp) DeepSeek33±12*local~104GB1Mllama.cpp › How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
152Molmo 72B (0924) Ai233±2local~309GBhow to run › LMArena leaderboard datasetMolmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding (Ai2, arXiv 2601.10611v4)Pixtral 12B (Mistral AI, arXiv 2410.07073v2)Ai2 Molmo-72B-0924 model card: Human Preference Elo Rating column
155Pixtral 12B (2409) Mistral30±2local~9.6GBllama.cpp › LMArena leaderboard datasetPixtral 12B (Mistral AI, arXiv 2410.07073v2)VisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback? (arXiv:2608.10408v1)Ai2 Molmo-72B-0924 model card: Human Preference Elo Rating column
156Gemma 3 12B Google30±4local~9.1GB131kLM Studio › Google DeepMind Gemma 3 270M IT model cardVisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback? (arXiv:2608.10408v1)Gemma Team — Gemma 3 Technical Report
157Llama 3.2 90B Vision Instruct Meta29±2local~58GB128kOllama › LMArena leaderboard datasetPixtral 12B (Mistral AI, arXiv 2410.07073v2)CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)
158InternVL2-26B Shanghai AI Laboratory (OpenGVLab)29±2local~55GBhow to run › LMArena leaderboard datasetCharXiv leaderboard (princeton-nlp/CharXiv README)OpenGVLab InternVL2 model cards (InternVL2-4B and InternVL2-26B), Evaluation tablesCapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding (arXiv:2501.16411v2)
161Qwen2-VL 7B Instruct Alibaba29±1local~6.4GBLM Studio › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)LMArena leaderboard datasetPixtral 12B (Mistral AI, arXiv 2410.07073v2)CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)Ai2 Molmo-72B-0924 model card: Human Preference Elo Rating column
163Ministral 3 3B Mistral27±4local~3.5GB262kLM Studio › CohereLabs/North-Micro-Vision-Instruct model card (benchmark table)
164Qwen3-VL 2B Instruct Alibaba27±1local~2.7GB256kllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)CohereLabs/North-Micro-Vision-Instruct model card (benchmark table)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
165Gemma 4 E2B Google27±3local~5.1GB131kllama.cpp › CohereLabs/North-Micro-Vision-Instruct model card (benchmark table)Gemma Team — Gemma 4 Technical Report
166Qwen2.5-VL 3B Instruct Alibaba27±2local~3.5GBllama.cpp › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)
167Qwen3.5 0.8B Alibaba26±2local~2GB262kllama.cpp › Qwen/Qwen3.5-2B model cardChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3)BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models (arXiv:2608.17895v1)How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings (arXiv:2605.07492v2)
169Aya Vision 32B Cohere25±2local~71GB16khow to run › LMArena leaderboard datasetKaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation (arXiv:2504.07072v2)VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark (arXiv:2508.13680v5)
170North Micro Vision Instruct (2.4B) Cohere24±4†local~3.8GB128khow to run › CohereLabs/North-Micro-Vision-Instruct model card (benchmark table)
171Molmo 7B-D (0924) Ai224±2local~35GBhow to run › LMArena leaderboard datasetMolmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding (Ai2, arXiv 2601.10611v4)Pixtral 12B (Mistral AI, arXiv 2410.07073v2)Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation (arXiv:2504.07072v2)Ai2 Molmo-72B-0924 model card: Human Preference Elo Rating column
172LLaVA-OneVision Qwen2 72B (ov-sft) LLaVA (lmms-lab)23±2local~155GBhow to run › LMArena leaderboard datasetCapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs (arXiv:2505.20740v3)
173Llama 3.2 11B Vision Instruct Meta22±2local~8.8GB128kOllama › LMArena leaderboard datasetPixtral 12B (Mistral AI, arXiv 2410.07073v2)
175CogVLM2 Llama3 Chat 19B Zhipu AI (THUDM)21±2local~43GBhow to run › LMArena leaderboard datasetCapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)Zhipu AI (THUDM) CogVLM2 model card, Benchmark table (own models)
176MiniCPM-V 2.6 OpenBMB21±2local~6.4GBllama.cpp › LMArena leaderboard datasetCharXiv leaderboard (princeton-nlp/CharXiv README)CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding (arXiv:2501.16411v2)
177InternVL2-4B Shanghai AI Laboratory (OpenGVLab)20±2local~10GBhow to run › LMArena leaderboard datasetOpenGVLab InternVL2 model cards (InternVL2-4B and InternVL2-26B), Evaluation tablesMicrosoft Phi-3.5-vision-instruct model card: Benchmarks tablePhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding (arXiv:2501.16411v2)
178LLaVA-v1.6-34B LLaVA19±2local~24GB4kOllama › LMArena leaderboard datasetCharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs (arXiv:2406.18521v1)CharXiv leaderboard (princeton-nlp/CharXiv README)CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (arXiv:2503.12329v1)LLaVA repository model zoo (haotian-liu/LLaVA docs/MODEL_ZOO.md)
179Phi-3.5-vision-instruct Microsoft16±2local~10GBhow to run › LMArena leaderboard datasetCohereLabs/North-Micro-Vision-Instruct model card (benchmark table)Microsoft Phi-3.5-vision-instruct model card: Benchmarks tableAi2 Molmo-72B-0924 model card: Human Preference Elo Rating columnPhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding (arXiv:2501.16411v2)
180Qwen2-VL 2B Instruct Alibaba14±2†local~2.8GB33kLM Studio › Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card)
181Gemma 3 4B Google14±4local~3.8GB131kLM Studio › Google DeepMind Gemma 3 270M IT model cardVisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback? (arXiv:2608.10408v1)Gemma Team — Gemma 3 Technical ReportVMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark (arXiv:2508.13680v5)
182Phi-3-vision-128k-instruct Microsoft12±2local~10GBhow to run › LMArena leaderboard datasetCharXiv leaderboard (princeton-nlp/CharXiv README)Phi-3 Technical Report (Microsoft, arXiv 2404.14219v3)PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding (arXiv:2501.16411v2)
—Command A+ (05-2026) Coherenot yet calibratedlocal~71GB128kllama.cpp › Cohere vendor-reported benchmark scores for its own models (cohere.com blog)
—EXAONE 4.5 33B LG AI Researchnot scored yetlocal~24GB262kllama.cpp ›

+ 101 more don't fit your machine or budget · show them

+ 2 models with fewer than 3 results left off, since one or two tests say little about overall ability · show them

184 of 202 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory