AImodelsComparison.com 1,011 models
Menu
Models Best of Trending Can I run it? Methodology About
1,011 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.

Task
All text-generation 400 text-to-image 150 ASR 89 image-text-to-text 82 sentence-similarity 55 feature-extraction 47 translation 44 text-classification 39 image-classification 32 token-classification 22 text-to-speech 16 audio-classification 12 image-segmentation 8 object-detection 8 summarization 7
Runs on
Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB
Licence
Size
$
400 models
#ModelParamsContextCommercial use30dMin VRAM
251 Qwen2.5-3B Qwen · text-generation 3.1 B 33 K other 310 K from 7.8 GB
252 Qwen3-8B-GGUF unsloth · text-generation — 41 K ✓ apache-2.0 309 K from 4.1 GB
253 Olmo-3-7B-Instruct-SFT allenai · text-generation 7.3 B 66 K ✓ apache-2.0 306 K from 17.7 GB
254 Qwen2-0.5B-Instruct Qwen · text-generation 490 M 33 K ✓ apache-2.0 305 K from 1.7 GB
255 Meta-Llama-3.1-8B-Instruct-GGUF bartowski · text-generation — — ⚠ llama3.1 302 K from 3.7 GB
256 T-lite-it-2.1 t-tech · text-generation 8.2 B 41 K ✓ apache-2.0 300 K from 19.7 GB
257 MiMo-7B-Base XiaomiMiMo · text-generation 7.8 B 33 K ✓ mit 299 K from 18.9 GB
258 Kimi-K2.5-NVFP4 nvidia · text-generation — — other 298 K from 650.4 GB
259 gemma-4-12B-coder-fable5-composer2.5-v1-GGUF yuxinlu1 · text-generation — — ✓ apache-2.0 298 K from 5.8 GB
260 Llama-3.2-1B-Instruct unsloth · text-generation 1.2 B 131 K ⚠ llama3.2 298 K from 3.4 GB
261 GLM-4.7-Flash unsloth · text-generation 31.2 B 203 K ✓ mit 295 K from 73.9 GB
262 DeepSeek-R1-Distill-Qwen-7B deepseek-ai · text-generation 7.6 B 131 K ✓ mit 295 K from 18.4 GB
263 SmolLM-135M HuggingFaceTB · text-generation 130 M 2 K ✓ apache-2.0 293 K from 1.1 GB
264 granite-4.0-h-tiny ibm-granite · text-generation 6.9 B 131 K ✓ apache-2.0 292 K from 16.8 GB
265 Meta-Llama-3-8B NousResearch · text-generation 8.0 B 8 K other 291 K from 19.4 GB
266 llama-7b huggyllama · text-generation 6.7 B 2 K other 288 K from 16.3 GB
267 Qwen3-Next-80B-A3B-Instruct Qwen · text-generation 81.3 B 262 K ✓ apache-2.0 287 K from 191.6 GB
268 DeepSeek-R1-0528-Qwen3-8B-MLX-4bit lmstudio-community · text-generation 1.3 B 131 K ✓ mit 285 K from 5.8 GB
269 opt-350m facebook · text-generation — 2 K other 283 K —
270 Qwen3-4B-GGUF Qwen · text-generation — — ✓ apache-2.0 280 K from 3.2 GB
271 gpt-j-6b EleutherAI · text-generation — — ✓ apache-2.0 279 K —
272 Qwen2.5-7B-Instruct-GPTQ-Int4 Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 276 K from 7.8 GB
273 Meta-Llama-3.1-8B-Instruct NousResearch · text-generation 8.0 B 131 K ⚠ llama3.1 276 K from 19.4 GB
274 Llama-3.2-1B-Instruct-Q8_0-GGUF hugging-quants · text-generation — — unknown 274 K from 2.0 GB
275 DeepSeek-V3.1 deepseek-ai · text-generation 684.5 B 164 K ✓ mit 268 K from 860.6 GB
276 gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2 yuxinlu1 · text-generation 12.0 B — ✓ apache-2.0 266 K from 28.6 GB
277 DeepSeek-R1-0528-Qwen3-8B-MLX-8bit lmstudio-community · text-generation 2.3 B 131 K ✓ mit 264 K from 10.4 GB
278 MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF GnLOLot · text-generation — — ✓ apache-2.0 261 K from 1.8 GB
279 Bielik-11B-v3.0-Instruct-awq speakleash · text-generation 11.3 B 33 K ✓ apache-2.0 259 K from 9.0 GB
280 pythia-410m EleutherAI · text-generation 510 M 2 K ✓ apache-2.0 257 K from 1.6 GB
281 Llama-3_3-Nemotron-Super-49B-v1_5-FP8 nvidia · text-generation 49.9 B 131 K other 256 K from 65.1 GB
282 Mistral-Small-24B-Instruct-2501-AWQ stelterlab · text-generation 23.6 B 33 K ✓ apache-2.0 255 K from 19.7 GB
283 Qwen3-Coder-30B-A3B-Instruct-AWQ QuantTrio · text-generation 30.5 B 262 K ✓ apache-2.0 254 K from 23.6 GB
284 droplychee-1.0-27b droplychee · text-generation 27.8 B — ✓ apache-2.0 252 K from 65.8 GB
285 LFM2.5-1.2B-Instruct-GGUF LiquidAI · text-generation — — other 252 K from 1.3 GB
286 DeepSeek-V3.2-Exp deepseek-ai · text-generation 685.4 B 164 K ✓ mit 252 K from 861.7 GB
287 llama-160m JackFram · text-generation 160 M 2 K ✓ apache-2.0 251 K from 1.2 GB
288 tiny_starcoder_py bigcode · text-generation 160 M — bigcode-openrail-m 249 K from 1.2 GB
289 Phi-3-mini-128k-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 249 K from 9.5 GB
290 llama-3-70b-instruct-awq casperhansen · text-generation 70.6 B 8 K unknown 249 K from 54.8 GB
291 Qwen3.5-122B-A10B-NVFP4 nvidia · text-generation 64.6 B — ✓ apache-2.0 249 K from 102.0 GB
292 DeepSeek-V4-Flash-GGUF bartowski · text-generation — — ✓ mit 245 K from 44.1 GB
293 pythia-14m EleutherAI · text-generation 10 M 2 K ✓ apache-2.0 239 K from 0.5 GB
294 Phi-3-vision-128k-instruct microsoft · text-generation 4.2 B 131 K ✓ mit 238 K from 10.2 GB
295 GLM-5.2-GGUF unsloth · text-generation — — ✓ mit 238 K from 52.0 GB
296 Qwen2.5-Coder-14B-Instruct-GPTQ-Int4 Qwen · text-generation 14.8 B 33 K ✓ apache-2.0 237 K from 13.7 GB
297 Qwen3-8B-GGUF Qwen · text-generation — — ✓ apache-2.0 236 K from 6.0 GB
298 NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 nvidia · text-generation 335.0 B 262 K other 233 K from 438.3 GB
299 Agents-A1-NVFP4 r0b0tlab · text-generation 18.9 B — ✓ apache-2.0 232 K from 29.5 GB
300 OLMoE-1B-7B-0125-Instruct allenai · text-generation 6.9 B 4 K ✓ apache-2.0 232 K from 16.8 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.