1,000 models · refreshed nightly

Text generation models

Every model in the catalog with its licence, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

#ModelParamsContextCommercial use30dMin VRAM
351 llava-onevision-qwen2-7b-ov lmms-lab · text-generation 8.0 B 33 K ✓ apache-2.0 185 K from 19.4 GB
352 Qwen2.5-3B-Instruct-GGUF Qwen · text-generation other 185 K from 2.0 GB
353 Qwen3-235B-A22B-GGUF unsloth · text-generation 41 K ✓ apache-2.0 184 K from 55.2 GB
354 Qwen3-14B-GGUF MaziyarPanahi · text-generation unknown 184 K from 6.8 GB
355 Qwen3-8B unsloth · text-generation 8.2 B 41 K ✓ apache-2.0 183 K from 19.7 GB
356 openai-gpt openai-community · text-generation 120 M ✓ mit 183 K from 1.0 GB
357 Qwen3-4B-unsloth-bnb-4bit unsloth · text-generation 4.1 B 41 K ✓ apache-2.0 183 K from 5.0 GB
358 Kimi-K2-Instruct moonshotai · text-generation 1,026.5 B 131 K other 181 K from 1,286.6 GB
359 Qwen3-14B-unsloth-bnb-4bit unsloth · text-generation 15.2 B 41 K ✓ apache-2.0 181 K from 15.0 GB
360 Kimi-K2.5 mlx-community · text-generation 1,026.4 B other 180 K from 877.8 GB
361 Qwen2.5-7B-Instruct-GGUF bartowski · text-generation ✓ apache-2.0 180 K from 3.6 GB
362 GLM-5-NVFP4 nvidia · text-generation 435.2 B 203 K ✓ mit 180 K from 594.6 GB
363 Qwen3-8B-GGUF MaziyarPanahi · text-generation unknown 180 K from 4.1 GB
364 Llama-3_3-Nemotron-Super-49B-v1 nvidia · text-generation 49.9 B 131 K other 179 K from 117.7 GB
365 LLaMmlein_1B_prerelease LSX-UniWue · text-generation 1.1 B 2 K other 179 K from 5.5 GB
366 Qwen3-1.7B-GGUF MaziyarPanahi · text-generation unknown 178 K from 1.5 GB
367 Phi-3-mini-4k-instruct-gptq-4bit kaitchup · text-generation 3.8 B 4 K unknown 178 K from 3.6 GB
368 Qwen3-32B-GGUF MaziyarPanahi · text-generation unknown 177 K from 14.1 GB
369 Qwen3-30B-A3B-GGUF MaziyarPanahi · text-generation unknown 177 K from 12.9 GB
370 Qwen3-Coder-Next-NVFP4-GB10 gdubicki · text-generation 262 K ✓ apache-2.0 176 K from 50.9 GB
371 starcoder2-3b bigcode · text-generation 3.0 B 16 K bigcode-openrail-m 176 K from 14.3 GB
372 Qwen3-30B-A3B-Thinking-2507-AWQ-4bit cyankiwi · text-generation 5.3 B 262 K ✓ apache-2.0 173 K from 21.2 GB
373 avibe AvitoTech · text-generation 7.9 B 33 K ✓ apache-2.0 173 K from 19.1 GB
374 Qwen3-235B-A22B-NVFP4 nvidia · text-generation 132.8 B 41 K ✓ apache-2.0 173 K from 168.0 GB
375 llama-3-8b-instruct-awq casperhansen · text-generation 8.0 B 8 K unknown 173 K from 8.0 GB
376 Qwen2.5-0.5B-Instruct-GGUF Qwen · text-generation ✓ apache-2.0 172 K from 1.0 GB
377 NVIDIA-Nemotron-Nano-9B-v2-FP8 nvidia · text-generation 8.9 B 131 K other 171 K from 13.1 GB
378 Qwen3-30B-A3B-FP8 Qwen · text-generation 30.5 B 41 K ✓ apache-2.0 171 K from 40.8 GB
379 Nemotron-Mini-4B-Instruct nvidia · text-generation 4 K other 170 K
380 granite-4.1-3b-GGUF ibm-granite · text-generation ✓ apache-2.0 170 K from 2.0 GB
381 Qwen3-14B-GPTQ-Int4 JunHowie · text-generation 14.8 B 41 K ✓ apache-2.0 170 K from 13.7 GB
382 LFM2.5-8B-A1B LiquidAI · text-generation 8.5 B 128 K other 170 K from 20.4 GB
383 falcon-mamba-7b tiiuae · text-generation 7.3 B other 170 K from 17.6 GB
384 Qwen2.5-7B-Instruct-bnb-4bit unsloth · text-generation 7.8 B 33 K ✓ apache-2.0 170 K from 7.8 GB
385 TinyLlama-1.1B-Chat-v0.3-AWQ TheBloke · text-generation 1.1 B 2 K ✓ apache-2.0 169 K from 1.5 GB
386 Meta-Llama-3-8B-Instruct NousResearch · text-generation 8.0 B 8 K other 169 K from 19.4 GB
387 DeepSeek-V3.2-AWQ QuantTrio · text-generation 685.4 B 164 K ✓ mit 168 K from 501.4 GB
388 NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit cyankiwi · text-generation 127.2 B 262 K other 168 K from 108.3 GB
389 Gemma-4-26B-A4B-it-NVFP4 bg-digitalservices · text-generation 15.1 B ✓ apache-2.0 168 K from 20.8 GB
390 Meta-Llama-3.1-8B-Instruct-AWQ-INT4 hugging-quants · text-generation 8.0 B 131 K ⚠ llama3.1 167 K from 8.0 GB
391 Qwen3-30B-A3B-GPTQ-Int4 Qwen · text-generation 30.5 B 41 K ✓ apache-2.0 167 K from 23.7 GB
392 GLM-4.5-Air-FP8 zai-org · text-generation 110.5 B 131 K ✓ mit 167 K from 140.9 GB
393 Agents-A1-4B InternScience · text-generation 4.5 B ✓ apache-2.0 167 K from 11.2 GB
394 Qwen2.5-Math-1.5B-Instruct Qwen · text-generation 1.5 B 4 K ✓ apache-2.0 167 K from 4.1 GB
395 RnJ-1-Instruct-FP8 Doradus-AI · text-generation 8.8 B 33 K ⚠ gemma 164 K from 15.0 GB
396 Qwen3-235B-A22B-FP8 Qwen · text-generation 235.1 B 41 K ✓ apache-2.0 163 K from 298.7 GB
397 Qwen3.5-122B-A10B-NVFP4 txn545 · text-generation 64.4 B ✓ apache-2.0 162 K from 101.3 GB
398 Llama-3.2-1B-Instruct-GGUF bartowski · text-generation ⚠ llama3.2 162 K from 1.2 GB
399 Phi-3.5-MoE-instruct microsoft · text-generation 41.9 B 131 K ✓ mit 161 K from 98.9 GB
400 Qwen3-4B-Instruct-2507-NVFP4 llmat · text-generation 2.8 B 262 K ✓ apache-2.0 161 K from 4.9 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.