1,423 models · 1,213 open weights · 210 API-only · refreshed nightly
Text generation models
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 | Min VRAM |
|---|---|---|---|---|---|---|
| 51 | GLM-5 | 753.9 B | 203 K | ✓ mit | 1.4 M | from 1,772.1 GB |
| 52 | Qwen2.5-3B-Instruct-AWQ | 3.4 B | 33 K | other | 1.4 M | from 4.0 GB |
| 53 | Qwen3.8-35B-A3B-Distill-GGUF | 35.0 B | — | ✓ apache-2.0 | 1.3 M | from 19.6 GB |
| 54 | Llama-3.2-1B-Instruct | 1.2 B | — | ⚠ llama3.2 | 1.3 M | from 3.4 GB |
| 55 | Qwen2.5-Coder-7B-Instruct | 7.6 B | 33 K | ✓ apache-2.0 | 1.3 M | from 18.4 GB |
| 56 | Ornith-1.5-397B-GGUF | — | — | ✓ mit | 1.3 M | from 1.5 GB |
| 57 | glm-5.3-exlr8-k2-k3-k4 | — | 1.0 M | other | 1.3 M | from 921.8 GB |
| 58 | GLM-4.5-Air | 110.5 B | 131 K | ✓ mit | 1.3 M | from 260.1 GB |
| 59 | Qwen2.5-VL-7B-Instruct-NVFP4 | 5.0 B | 128 K | other | 1.2 M | from 9.2 GB |
| 60 | Llama-3.2-1B-Instruct | 1.2 B | 131 K | ⚠ llama3.2 | 1.2 M | from 3.4 GB |
| 61 | MiniMax-M2.5 | 228.7 B | 197 K | other | 1.2 M | from 288.0 GB |
| 62 | GLM-5.3-Flash-Maya-GGUF | 321.3 B | — | ✓ mit | 1.2 M | from 49.9 GB |
| 63 | Qwen2.5-0.5B | 490 M | 33 K | ✓ apache-2.0 | 1.2 M | from 1.7 GB |
| 64 | Hy3 | 298.8 B | 262 K | ✓ apache-2.0 | 1.2 M | from 702.7 GB |
| 65 | OTel-2.0-LLM-31B-IT-QLoRA | 31.3 B | — | ✓ apache-2.0 | 1.2 M | from 74.0 GB |
| 66 | DeepSeek-V4-Flash | 158.1 B | 1.0 M | ✓ mit | 1.2 M | from 199.8 GB |
| 67 | Gemma-4-31B-IT-NVFP4 | 20.9 B | — | other | 1.1 M | from 39.5 GB |
| 68 | Qwen2.5-14B-Instruct-AWQ | 14.8 B | 33 K | ✓ apache-2.0 | 1.1 M | from 13.7 GB |
| 69 | Qwen3-0.6B | 752 M | 41 K | ✓ apache-2.0 | 1.1 M | from 2.3 GB |
| 70 | Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF | 27.0 B | — | ✓ apache-2.0 | 1.1 M | from 12.9 GB |
| 71 | Qwen3-30B-A3B | 30.5 B | 41 K | ✓ apache-2.0 | 1.1 M | from 72.3 GB |
| 72 | Ornith-1.5-9B-NVFP4 | 6.7 B | — | ✓ mit | 1.1 M | from 11.2 GB |
| 73 | Ornith-1.5-35B-A3B-NVFP4 | 19.5 B | — | ✓ mit | 1.1 M | from 29.2 GB |
| 74 | Qwen3-Coder-30B-A3B-Instruct-FP8 | 30.5 B | 262 K | ✓ apache-2.0 | 1.1 M | from 39.4 GB |
| 75 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 | 31.6 B | 262 K | other | 1.1 M | from 77.6 GB |
| 76 | NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 | 560.5 B | 262 K | other | 1.1 M | from 1,317.7 GB |
| 77 | MiniCPM5-2B | 2.5 B | 131 K | ✓ apache-2.0 | 1.1 M | from 6.4 GB |
| 78 | GLM-4.7-Flash | 31.2 B | 203 K | ✓ mit | 1.0 M | from 73.9 GB |
| 79 | NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | 123.6 B | 262 K | other | 1.0 M | from 291.0 GB |
| 80 | tiny-gpt2 | — | — | unknown | 1.0 M | — |
| 81 | Ternary-Bonsai-27B-mlx-2bit | 2.6 B | — | ✓ apache-2.0 | 1.0 M | from 10.2 GB |
| 82 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 | 17.8 B | 1.0 M | other | 1.0 M | from 26.9 GB |
| 83 | Bonsai-27B-mlx-1bit | 1.7 B | — | ✓ apache-2.0 | 1.0 M | from 6.4 GB |
| 84 | Qwen2.5-Coder-32B-Instruct-AWQ | 32.8 B | 33 K | ✓ apache-2.0 | 972 K | from 26.7 GB |
| 85 | Ornith-1.0-35B-FP8 | 35.1 B | — | ✓ mit | 945 K | from 47.2 GB |
| 86 | TinyLlama-1.1B-Chat-v1.0 | 1.1 B | 2 K | ✓ apache-2.0 | 944 K | from 3.1 GB |
| 87 | Qwen2.5-32B-Instruct-AWQ | 32.8 B | 33 K | ✓ apache-2.0 | 923 K | from 26.7 GB |
| 88 | gpt2-large | 810 M | — | ✓ mit | 908 K | from 4.2 GB |
| 89 | Qwen3-30B-A3B-Instruct-2507 | 30.5 B | 262 K | ✓ apache-2.0 | 896 K | from 72.3 GB |
| 90 | JiRackUltra_1b | 1.8 B | 131 K | ✓ mit | 891 K | from 1.8 GB |
| 91 | LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF | 24.0 B | 131 K | other | 881 K | from 15.7 GB |
| 92 | GLM-5.1 | 753.9 B | 203 K | ✓ mit | 879 K | from 1,772.1 GB |
| 93 | Sharp-Spark-X2.5-4B-GGUF | 4.0 B | — | ✓ apache-2.0 | 874 K | from 1.1 GB |
| 94 | Llama-3.2-3B-Instruct | 3.2 B | — | ⚠ llama3.2 | 872 K | from 8.0 GB |
| 95 | Ornith-1.5-122B-GGUF | 122.0 B | — | ✓ mit | 871 K | from 102.2 GB |
| 96 | Laguna-XS.2 | 33.4 B | 262 K | ✓ apache-2.0 | 860 K | from 79.1 GB |
| 97 | SmolLM2-135M-Instruct | 130 M | 8 K | ✓ apache-2.0 | 847 K | from 0.8 GB |
| 98 | Qwen3-8B-GGUF | — | — | ✓ apache-2.0 | 826 K | from 6.0 GB |
| 99 | Laguna-M.1 | 225.8 B | 262 K | ✓ apache-2.0 | 824 K | from 531.1 GB |
| 100 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8 | 31.6 B | 262 K | unknown | 820 K | from 40.8 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.