AImodelsComparison.com 1,058 models
Menu
Models Best of Trending Can I run it? Methodology About
1,058 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 413 text-to-image 152 ASR 92 image-text-to-text 89 sentence-similarity 60 feature-extraction 48 translation 48 text-classification 42 image-classification 33 token-classification 29 text-to-speech 12 audio-classification 11 object-detection 11 image-segmentation 10 summarization 8
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
$
413 models
#ModelParamsContextCommercial use30dMin VRAM
301 mamba-130m-hf state-spaces · text-generation 130 M — unknown 281 K from 1.1 GB
302 DeepSeek-V3.1 deepseek-ai · text-generation 684.5 B 164 K ✓ mit 278 K from 860.6 GB
303 Llama-3.2-3B-Instruct-FP8-dynamic RedHatAI · text-generation 3.6 B 131 K ⚠ llama3.2 277 K from 5.9 GB
304 Meta-Llama-3-8B meta-llama · text-generation · gated 8.0 B — ⚠ llama3 275 K from 19.4 GB
305 MiniCPM5-2B-DSpark openbmb · text-generation 324 M 131 K ✓ apache-2.0 275 K from 1.3 GB
306 Qwen3-14B-GGUF MaziyarPanahi · text-generation — — unknown 274 K from 6.8 GB
307 gemma-4-31B-it-scotoma-2-GGUF ReadyArt · text-generation — — ✓ apache-2.0 274 K from 13.8 GB
308 Qwen3-4B-GGUF MaziyarPanahi · text-generation — — unknown 272 K from 2.3 GB
309 tiny_starcoder_py bigcode · text-generation 160 M — bigcode-openrail-m 272 K from 1.2 GB
310 Qwen2.5-Coder-7B-Instruct-GGUF Qwen · text-generation — — ✓ apache-2.0 272 K from 3.8 GB
311 gpt-oss-20b-MXFP4-Q8 mlx-community · text-generation 20.9 B 131 K ✓ apache-2.0 271 K from 16.9 GB
312 DeepSeek-R1-Distill-Qwen-7B deepseek-ai · text-generation 7.6 B 131 K ✓ mit 271 K from 18.4 GB
313 MiniMax-M2 MiniMaxAI · text-generation 228.7 B 197 K other 271 K from 288.0 GB
314 DeepSeek-R1-0528-Qwen3-8B-MLX-8bit lmstudio-community · text-generation 2.3 B 131 K ✓ mit 271 K from 10.4 GB
315 Qwen3-1.7B-GGUF MaziyarPanahi · text-generation — — unknown 270 K from 1.5 GB
316 Qwen3-0.6B-FP8 Qwen · text-generation 750 M 41 K ✓ apache-2.0 270 K from 1.8 GB
317 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF ggml-org · text-generation — — other 269 K from 21.3 GB
318 Qwen3-8B-GGUF MaziyarPanahi · text-generation — — unknown 269 K from 4.1 GB
319 Qwen3-4B-AWQ Qwen · text-generation 4.0 B 41 K ✓ apache-2.0 268 K from 4.0 GB
320 taardis-27b-full-ternary CodeMasterCody3D · text-generation — — ✓ apache-2.0 268 K from 8.4 GB
321 Qwen3-30B-A3B-GGUF MaziyarPanahi · text-generation — — unknown 266 K from 12.9 GB
322 Qwen3-32B-GGUF MaziyarPanahi · text-generation — — unknown 266 K from 14.1 GB
323 openai-gpt openai-community · text-generation 120 M — ✓ mit 265 K from 1.0 GB
324 Qwen3-30B-A3B-GGUF Qwen · text-generation — — ✓ apache-2.0 265 K from 20.9 GB
325 llama-3-8b-instruct-awq casperhansen · text-generation 8.0 B 8 K unknown 265 K from 8.0 GB
326 Apodex-1.1-mini-GGUF abenzerps · text-generation — — ✓ apache-2.0 264 K from 10.2 GB
327 Llama-Guard-3-1B alpindale · text-generation 1.5 B 131 K ⚠ llama3.2 264 K from 4.0 GB
328 Llama-3.2-1B-Instruct unsloth · text-generation 1.2 B 131 K ⚠ llama3.2 262 K from 3.4 GB
329 Spark-X2.5-4B-GGUF XHToken · text-generation 4.0 B — ✓ apache-2.0 259 K from 4.0 GB
330 Qwen2.5-Coder-7B-Instruct-4bit mlx-community · text-generation 1.2 B 33 K ✓ apache-2.0 258 K from 5.4 GB
331 EuroLLM-22B-Instruct-2512 utter-project · text-generation 22.6 B 33 K ✓ apache-2.0 257 K from 53.7 GB
332 droplychee-1.0-27b droplychee · text-generation 27.8 B — ✓ apache-2.0 252 K from 65.8 GB
333 DeepSeek-R1-0528 deepseek-ai · text-generation 684.5 B 164 K ✓ mit 252 K from 860.6 GB
334 Qwen3-Coder-Next-FP8 unsloth · text-generation 79.7 B 262 K ✓ apache-2.0 250 K from 100.9 GB
335 Meta-Llama-3.1-8B-Instruct unsloth · text-generation 8.0 B 131 K ⚠ llama3.1 250 K from 19.4 GB
336 Hy3-GGUF vcruz305 · text-generation — — ✓ apache-2.0 248 K from 52.9 GB
337 sarashina2.2-0.5b-instruct-v0.1 sbintuitions · text-generation 790 M 8 K ✓ mit 248 K from 2.4 GB
338 Qwen3.8-27B-NVFP4-MTP-GGUF esatapedico · text-generation — — ✓ apache-2.0 248 K from 36.9 GB
339 SmolLM2-1.7B-Instruct HuggingFaceTB · text-generation 1.7 B 8 K ✓ apache-2.0 247 K from 4.5 GB
340 Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF hesamation · text-generation — — ✓ apache-2.0 245 K from 23.8 GB
341 DeepSeek-V4-Flash-GGUF bartowski · text-generation — — ✓ mit 245 K from 44.1 GB
342 OTel-LLM-8B-A1B-IT farbodtavakkoli · text-generation — 128 K ✓ apache-2.0 245 K —
343 Meta-Llama-3.1-8B-Instruct-AWQ-INT4 hugging-quants · text-generation 8.0 B 131 K ⚠ llama3.1 245 K from 8.0 GB
344 gemma-4-31B-it-uncensored TrevorJS · text-generation 32.7 B — ✓ apache-2.0 244 K from 74.2 GB
345 SmolLM2-1.7B HuggingFaceTB · text-generation 1.7 B 8 K ✓ apache-2.0 243 K from 4.5 GB
346 h2ovl-mississippi-800m h2oai · text-generation 830 M — ✓ apache-2.0 242 K from 2.4 GB
347 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark nvidia · text-generation 760 M 1.0 M other 241 K from 2.1 GB
348 llama-7b huggyllama · text-generation 6.7 B 2 K other 241 K from 16.3 GB
349 pythia-410m EleutherAI · text-generation 510 M 2 K ✓ apache-2.0 241 K from 1.6 GB
350 Qwen3-8B-FP8 nvidia · text-generation 8.2 B 41 K ✓ apache-2.0 240 K from 12.1 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.