Best image models for a 12GB graphics card
A leaderboard of the best image models for a 12GB graphics card (with 32GB of system RAM). The best one that runs on it right now is Qwen-Image-2.1, followed by Ideogram 4.0 and HiDream-O1-Image. Models are ranked by one score that combines 73 published benchmarks. Models that run on it show the download that fits and the command to run it.
140 models · scores combine 73 benchmarks · updated how it works · find a leaderboard · benchmark your machine
Models for 32GB RAM · 12GB graphics card → ~12GB fast · reset
+ more
$ terminal
↗ share
detecting your OS…
Score vs API price
x
show
● open weights ◆ API only ─┘ best score for the price · x: USD per image (log)
| # | model | score↓ | where↓ | speed↓ | sources |
|---|---|---|---|---|---|
| 1 |  GPT Image 2.5 Sunburst | 92±2 | api $0.013/image |     | |
| 2 | GPT Image 2.5 Flare | 88±2 | api $0.013/image | | |
| 3 | GPT Image 2 | 85±1 | api $0.053/image | +5 | |
| 5 |  Nano Banana 2.1 | 81±2* | api $0.034/image | | |
| 6 |  Grok Imagine Image 2.0 | 79±2 | api $0.040/image | | |
| 7 |  Reve 2.1 | 78±2 | api $0.25/image | | |
| 8 |  Muse Image | 76±2 | api $0.010/image | | |
| 9 | Nano Banana 2 (Gemini 3.1 Flash Image) | 76±1 | api $0.067/image | +7 | |
| 10 | Nano Banana Pro (Gemini 3 Pro Image) | 76±1 | api $0.13/image | +10 | |
| 11 |  Qwen-Image-3.0-Pro | 75±2 | api $0.040/image | | |
| 12 |  Seedream 5.0 Pro | 75±2 | api $0.050/image | | |
| 13 | Reve 2.0 | 74±2* | api $0.25/image | | |
| 14 | ChatGPT Image Latest (chatgpt-image-latest) | 74±4* | api $0.034/image | | |
| 16 | Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) | 73±2 | api $0.034/image | | |
| 17 | GPT Image 1.5 | 71±1 | api $0.034/image | +5 | |
| 18 | Qwen-Image-2.1 · int8 convrot + Qwen3-VL 8B q4_k_m (sd.cpp) | 69±2 | local (slow) | | |
| 20 | Qwen-Image-2.0-Pro (2026-06-22) | 67±2* | api $0.075/image | | |
| 21 |  Uni-1.1 | 67±2* | api $0.040/image | | |
| 23 |  Ideogram 4.0 · nf4 | 66±2* | local | | |
| 24 | Qwen-Image 2.0 Pro | 66±3 | api $0.075/image | | |
| 26 | Grok Imagine Image | 66±2 | api $0.020/image | | |
| 27 | Uni-1.1 Max | 65±2 | api $0.10/image | | |
| 28 | Grok Imagine Image Pro | 65±2 | api $0.050/image | | |
| 29 | Seedream 5.0 Lite | 65±2 | api $0.035/image | +2 | |
| 30 |  Seedream 4.5 | 64±1 | api $0.040/image | +1 | |
| 31 |  Recraft V4.1 Utility Pro | 64±2* | api $0.21/image | | |
| 32 |  FLUX.2 [max] | 64±1 | api $0.070/image | | |
| 33 |  Wan 2.7 Image Pro | 63±2 | api $0.075/image | | |
| 36 | FLUX.2 [pro] | 63±2 | api $0.030/image | | |
| 37 | FLUX.2 [flex] | 62±2 | api $0.050/image | | |
| 38 |  HunyuanImage 3.0-Instruct | 62±3* | api $0.090/image | | |
| 39 | Nano Banana (Gemini 2.5 Flash Image) | 62±1 | api $0.039/image |  +10 | |
| 40 | Wan 2.7 Image | 62±2 | api $0.030/image | | |
| 41 | Imagen 4 Ultra | 61±2 | api $0.060/image | | |
| 42 | GPT Image 1 | 61±1 | api $0.042/image | +9 | |
| 43 | Wan 2.6 Text-to-Image | 61±3* | api $0.030/image | | |
| 45 | Seedream 4.0 | 61±1 | api $0.040/image | +5 | |
| 46 | Recraft V4.1 Pro | 61±3* | api $0.21/image | | |
| 47 |  ERNIE-Image-Turbo | 61±3† | api $0.010/image +local | | |
| 49 | ERNIE-Image | 60±2 | api $0.030/image +local | | |
| 50 |  Kling Image O1 | 60±4* | api $0.028/image | | |
| 51 |  Krea 2 Medium | 60±3* | api $0.030/image | | |
| 52 | Imagen 4 | 59±2 | api $0.040/image | | |
| 53 | Wan 2.5 Text-to-Image Preview | 59±3* | api $0.030/image | | |
| 54 | Recraft V4 | 59±3* | api $0.040/image | | |
| 56 | Krea 2 Turbo | 59±3* | api $0.015/image +local | | |
| 57 | GPT Image 1 Mini | 59±2 | api $0.011/image | | |
| 58 | Krea 2 Large | 59±3* | api $0.060/image | | |
| 59 | Qwen-Image-Edit-2509 | 59±3 | api $0.030/image +local | | |
| 60 |  HiDream-O1-Image · fp8 | 58±2 | local | | |
| 61 | FLUX.2 [dev] | 58±1 | api $0.046/image +local | +8 | |
| 63 |  Z-Image (Base) · gguf-q4_k_m + Qwen3 4B q4_k_m (sd.cpp) | 58±2 | local | | |
| 64 | Wan 2.6 Image | 58±4* | api $0.030/image | | |
| 65 | HunyuanImage 2.1 | 58±2* | api $0.10/image | | |
| 66 | Qwen-Image-Edit-2511 | 58±2 | api $0.030/image | +2 | |
| 67 | Recraft V4.1 Flash | 57±3* | api $0.0070/image | | |
| 68 | HunyuanImage 3.0 | 57±2 | api $0.080/image | +3 | |
| 72 |  LongCat-Image-Edit | 56±2 | api $0.15/image | | |
| 74 |  P-Image-Edit | 56±4* | api $0.010/image | | |
| 76 | Qwen-Image-2512 | 56±1 | api $0.020/image +local | +1 | |
| 78 | Z-Image-Turbo · gguf-q3_k (+ Qwen3-4B Q4_K_M text encoder) | 55±1 | local | +1 | |
| 79 |  LLaDA-Image · gguf-q8_0 + LLaDA2 text encoder q4_k (sd.cpp) | 55±3† | local (slow) | | |
| 80 | Qwen-Image-Edit | 55±2 | api $0.030/image +local | +4 | |
| 82 | FLUX.2 [klein] 9B | 55±2 | api $0.015/image +local | | |
| 83 | FLUX.1 Kontext [max] | 55±2 | api $0.080/image | | |
| 85 | Qwen-Image | 54±1 | api $0.025/image +local | +8 | |
| 87 | LLaDA-Image-Turbo · gguf-q8_0 + LLaDA2 text encoder q4_k (sd.cpp) | 54±3† | local (slow) | | |
| 88 | LongCat-Image | 53±4 | api $0.13/image +local | | |
| 90 | Kling Image 2.1 | 53±7* | api $0.014/image | | |
| 92 | Wan 2.5 Image-to-Image Preview | 53±4* | api $0.030/image | | |
| 93 |  MiniMax image-01 | 53±5* | api $0.0035/image | | |
| 94 | Ideogram 3.0 | 52±2 | api $0.060/image | | |
| 97 | FLUX.2 [klein] 4B · bf16 (cpu offload) | 52±2 | local | | |
| 98 | P-Image | 51±2* | api $0.0050/image | | |
| 99 | Photon | 51±2 | api $0.019/image | | |
| 100 | Recraft V3 | 50±2 | api $0.040/image | | |
| 101 | FLUX.1 Kontext [pro] | 50±2 | api $0.040/image | | |
| 102 |  GLM-Image | 50±2 | api $0.015/image | | |
| 104 |  Runway Gen-4 Image | 50±3* | api $0.050/image | | |
| 105 |  Lucid Origin | 49±3* | api $0.017/image | | |
| 106 |  Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M) · fp32 | 48±15* | local | | |
| 107 |  Kandinsky 3 · fp16 | 48±11* | local (slow) | | |
| 110 |  VQ-Diffusion (ITHQ) · fp16 | 48±15* | local | | |
| 113 |  Ovis-Image-7B · bf16 | 48±7* | local (slow) | | |
| 114 | FLUX.1 Krea [dev] | 47±3 | api $0.025/image | | |
| 116 | HiDream-I1-Full | 47±2 | api $0.050/image | | |
| 118 | Ideogram 2.0 | 46±2 | api $0.080/image | | |
| 120 | FLUX1.1 [pro] | 46±2 | api $0.040/image | | |
| 126 | FLUX.1 Kontext [dev] | 44±1 | api $0.025/image +local | +7 | |
| 127 | FLUX.1 [dev] · fp8 (layerwise casting) | 44±1 | local | +5 | |
| 129 | UNO · fp8 FLUX.1-dev base + UNO LoRA, CPU offload | 43±4* | local (slow) | | |
| 131 |  Lumina-Image 2.0 | 43±4* | api $0.075/image +local | | |
| 133 | BAGEL | 42±1 | api $0.10/image +local | +14 | |
| 135 | FLUX.1 [schnell] | 42±2 | api $0.0030/image +local | | |
| 136 |  OmniGen2 | 42±2 | api $0.15/image +local | +6 | |
| 137 |  Stable Diffusion 3.5 Large · fp8 (TensorRT) | 42±1 | local | +4 | |
| 138 |  Show-o2 7B · official scripts (checkpoint as stored) | 42±3 | local (slow) | | |
| 139 |  Playground v2 (1024px aesthetic) · fp16 | 41±4* | local | | |
| 140 | Playground v2.5 · fp16 | 41±2 | local | +1 | |
| 141 | Stable Diffusion 3.5 Medium | 41±3 | api $0.035/image +local | | |
| 146 | Show-o2 1.5B-HQ · official scripts (checkpoint as stored) | 40±3* | local | | |
| 148 | Stable Diffusion XL 0.9 (base) · fp16 | 40±6* | local | | |
| 149 | Stable Diffusion 3 Medium · q8_0 (sd.cpp --type) | 40±2 | local | | |
| 150 |  Kolors · fp16 | 39±3 | local (slow) | | |
| 152 | Stable Cascade · bf16 prior + fp16 decoder, model CPU offload | 38±4* | local (slow) | | |
| 153 |  Janus-Pro-7B | 38±2 | api $0.0020/image +local | | |
| 156 | SDXL-Lightning (4-step UNet) · fp16 | 37±3* | local | | |
| 157 | Kandinsky 2.2 · fp16 | 37±5*† | local (slow) | | |
| 158 | Janus-Pro-1B · bf16 | 36±4 | local | | |
| 159 | Show-o (show-o-demo-512) · fp32 | 36±3* | local | | |
| 161 |  SSD-1B · fp16 (sd.cpp) | 36±4* | local | | |
| 163 |  PixArt-α (PixArt-XL-2-1024-MS) · fp16 | 36±2 | local (slow) | | |
| 164 | Emu3 · bf16 | 36±2 | local (slow) | | |
| 166 |  IF-XL · fp16 + model CPU offload (stages I+II, 256px) | 35±2 | local (slow) | +1 | |
| 167 | Stable Diffusion XL 1.0 · fp16 | 34±1 | local | +8 | |
| 168 |  LCM-SDXL · fp16 | 34±3 | local | | |
| 169 | OmniGen (v1) · official OmniGen package, default settings | 34±4 | local | | |
| 170 | SDXL-Turbo · fp16 | 34±2 | local | | |
| 171 | IF-L · fp16 + model CPU offload (stages I+II, 256px) | 33±3 | local (slow) | | |
| 174 |  VILA-U 7B (256px) · bf16 (official inference.py) | 32±7* | local (slow) | | |
| 175 | LCM-SSD-1B · fp16 | 32±4* | local | | |
| 176 | Janus-1.3B · bf16 | 32±4 | local | | |
| 177 | IF-M · fp16 + model CPU offload (stages I+II, 256px) | 31±3 | local (slow) | | |
| 178 |  Dreamlike Photoreal 2.0 · fp16 | 30±3 | local | | |
| 182 |  Versatile Diffusion v1.0 · fp16 | 29±4 | local | | |
| 183 |  DALL·E Mega (minDALL-E) · fp32 | 29±4 | local | | |
| 185 |  Openjourney · fp16 | 28±2 | local | | |
| 186 | Stable Diffusion v1.4 · fp16 | 27±2 | local | | |
| 187 | Stable Diffusion v1.3 · fp16 | 27±4* | local | | |
| 188 | Stable Diffusion v1.1 · fp16 | 26±3 | local | | |
| 189 | Stable Diffusion v1.2 · fp16 | 26±3* | local | | |
| 191 | Stable Diffusion v1.5 · fp16 | 26±2 | local | +1 | |
| 192 | OneCAT-3B · bf16 (official generate_txt2img.py) | 24±5* | local (slow) | | |
| 193 | LCM Dreamshaper v7 · fp32 | 23±4* | local | | |
| 194 |  InstructPix2Pix · fp16 | 19±3 | local | | |
| 197 |  CogView2 · fp16 (--fp16), first stage only | 1±4 | local (slow) | | |
| — | Kandinsky 2.1 · fp16 | not scored yet | local (slow) | ||
| — | Mage-Flow · int8 convrot + Qwen3-VL 4B q4_k_m (sd.cpp) | not yet calibrated | local | | |
| — | Mage-Flow-Base · bf16 + Qwen3-VL 4B q4_k_m (sd.cpp) | not yet calibrated | local (slow) | | |
| — | Mage-Flow-Turbo · int8 convrot + Qwen3-VL 4B q4_k_m (sd.cpp) | not yet calibrated | local | |
+ 62 more don't fit your machine or budget · show them
202 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