1,423 models · 1,213 open weights · 210 API-only · refreshed nightly
Models that run on Mac M3 · 24 GB
Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.
| # | Model | Params | Context | Commercial use | 30d | On Mac M3 · 24 GB |
|---|---|---|---|---|---|---|
| 651 | AWPainting-v1-2 | 860 M | — | ⚠ creativeml-openrail-m | 64 K | 15.0 GB |
| 652 | mbart-large-50-many-to-many-mmt | 610 M | 1 K | unknown | 63 K | 3.3 GB |
| 653 | sarvam-translate | 4.3 B | — | gpl-3.0 | 61 K | 10.6 GB |
| 654 | flux-3-image-klein-GGUF | — | — | unknown | 61 K | 3.0 GB |
| 655 | MEETING_SUMMARY | 410 M | 1 K | ✓ apache-2.0 | 61 K | 2.3 GB |
| 656 | Lusty_Krea-2_NSFW | 12.8 B | — | other | 61 K | 11.6 GB |
| 657 | Qwen-Image-2.1-Turbo-Uncensored-GGUF | 8.8 B | — | ✓ apache-2.0 | 60 K | 5.5 GB |
| 658 | majicMIX_realistic_v7 | 860 M | — | other | 60 K | 12.0 GB |
| 659 | Qwen-Image-2.1-Uncensored-Abenzerps-GGUF | 7.1 B | — | other | 59 K | 6.1 GB |
| 660 | animagine-xl-3.0 | 2.6 B | — | ⚠ openrail++ | 59 K | 16.1 GB |
| 661 | one-obsession-17-red-sdxl | 2.6 B | — | other | 57 K | 8.5 GB |
| 662 | HY-MT1.5-1.8B-GGUF | 1.8 B | — | unknown | 56 K | 2.0 GB |
| 663 | Anima-LLLite | — | — | other | 56 K | 0.8 GB |
| 664 | FLUX.1-dev-GGUF | 11.9 B | — | other | 55 K | 6.7 GB |
| 665 | controlnet-canny-sdxl-1.0 | 1.3 B | — | ⚠ openrail++ | 55 K | 8.9 GB |
| 666 | FLUX-3-Image-Klein_GGUFs | — | — | unknown | 55 K | 4.2 GB |
| 667 | controlnet-tile-sdxl-1.0 | 1.3 B | — | ✓ apache-2.0 | 53 K | 3.4 GB |
| 668 | financial-summarization-pegasus | 570 M | 512 | unknown | 52 K | 3.1 GB |
| 669 | Juggernaut-X-v10 | — | — | ⚠ creativeml-openrail-m | 52 K | 8.3 GB |
| 670 | Sugoi-32B-Ultra-GGUF | — | — | ✓ apache-2.0 | 50 K | 14.0 GB |
| 671 | indictrans2-en-indic-1B | 1.1 B | — | ✓ mit | 48 K | 5.6 GB |
| 672 | Nemotron-3.5-Content-Safety | 4.3 B | — | other | 45 K | 10.6 GB |
| 673 | nllb-200-1.3B | 1.3 B | 1 K | ✗ cc-by-nc-4.0 | 43 K | 3.6 GB |
| 674 | wmt19-en-de | 272 M | 1 K | ✓ apache-2.0 | 35 K | 1.7 GB |
| 675 | byt5-leetspeak-decoder | 582 M | — | ✓ mit | 35 K | 3.1 GB |
| 676 | wmt19-de-en | 272 M | 1 K | ✓ apache-2.0 | 32 K | 1.7 GB |
| 677 | HY-MT1.5-7B-GGUF | 7.0 B | — | unknown | 30 K | 6.6 GB |
| 678 | Hy-MT2-1.8B | 2.0 B | 262 K | ✓ apache-2.0 | 26 K | 5.3 GB |
| 679 | moondream3.1-9B-A2B | 9.3 B | — | other | 10 K | 13.4 GB |
| 680 | reka-edge-2603 | 7.1 B | — | other | 1 K | 17.3 GB |
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.