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
251 GLM-5.2-GGUF unsloth · text-generation — — ✓ mit 352 K from 52.0 GB
252 amd.Instella-MoE-16B-A3B-Think-GGUF DevQuasar · text-generation — — unknown 351 K from 7.7 GB
253 Qwen3-235B-A22B Qwen · text-generation 235.1 B 41 K ✓ apache-2.0 348 K from 553.0 GB
254 Agents-A1-4B InternScience · text-generation 4.5 B — ✓ apache-2.0 344 K from 11.2 GB
255 NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 nvidia · text-generation 302.8 B 262 K other 343 K from 433.5 GB
256 Ling-3.0-flash-GGUF AtomicChat · text-generation — — ✓ mit 341 K from 36.1 GB
257 Ornith-1.5-9B-MLX-8bit ornith-ai · text-generation 9.0 B — unknown 341 K from 12.3 GB
258 Ornith-1.5-9B-MLX ornith-ai · text-generation 9.0 B — unknown 341 K from 21.5 GB
259 Phi-3.5-mini-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 341 K from 9.5 GB
260 DeepSeek-R1-Distill-Qwen-14B deepseek-ai · text-generation 14.8 B 131 K ✓ mit 340 K from 35.2 GB
261 Hy3-GGUF AngelSlim · text-generation — — ✓ apache-2.0 340 K from 101.4 GB
262 Qwen2.5-3B Qwen · text-generation 3.1 B 33 K other 338 K from 7.8 GB
263 Qwopus3.6-27B-Fusion-GGUF KyleHessling1 · text-generation — — other 337 K from 15.4 GB
264 Dolphin-Mistral-24B-Venice-Edition dphn · text-generation 24.0 B — ✓ apache-2.0 333 K from 56.9 GB
265 Qwen3.8-27B-DSpark RadixArk · text-generation 1.9 B 262 K other 329 K from 4.9 GB
266 Qwen3-Coder-30B-A3B-Instruct-AWQ QuantTrio · text-generation 30.5 B 262 K ✓ apache-2.0 329 K from 23.6 GB
267 GigaChat3.1-Audio-10B-A1.8B ai-sage · text-generation — — ✓ mit 329 K from 26.6 GB
268 LFM2.5-1.2B-Instruct-GGUF LiquidAI · text-generation — — other 325 K from 1.3 GB
269 MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF GnLOLot · text-generation — — ✓ apache-2.0 325 K from 1.3 GB
270 MiniMax-M2.5 MiniMaxAI · text-generation 228.7 B 197 K other 324 K from 288.0 GB
271 Meta-Llama-3.1-8B-Instruct-GGUF bartowski · text-generation — — ⚠ llama3.1 320 K from 3.7 GB
272 Qwen3-Next-80B-A3B-Instruct Qwen · text-generation 81.3 B 262 K ✓ apache-2.0 319 K from 191.6 GB
273 Qwen3.6-27B-MTP-pi-tune-GGUF bytkim · text-generation — — ✓ apache-2.0 319 K from 12.5 GB
274 Qwen2.5-Math-1.5B-Instruct Qwen · text-generation 1.5 B 4 K ✓ apache-2.0 318 K from 4.1 GB
275 gpt2-medium openai-community · text-generation 380 M — ✓ mit 317 K from 2.2 GB
276 xflux_text_encoders XLabs-AI · text-generation 4.8 B — ✓ apache-2.0 317 K from 11.7 GB
277 Meta-Llama-3.1-8B-Instruct NousResearch · text-generation 8.0 B 131 K ⚠ llama3.1 317 K from 19.4 GB
278 CodeLlama-7b-hf codellama · text-generation 6.7 B 16 K ⚠ llama2 316 K from 16.3 GB
279 The_GuageLLM_23M Hai929 · text-generation 20 M — ✓ apache-2.0 314 K from 0.6 GB
280 opt-350m facebook · text-generation 350 M 2 K other 308 K from 1.3 GB
281 gpt-j-6b EleutherAI · text-generation 6.0 B — ✓ apache-2.0 304 K from 14.6 GB
282 sarvam-30b sarvamai · text-generation 32.2 B 131 K ✓ apache-2.0 304 K from 146.8 GB
283 DeepSeek-V2-Lite deepseek-ai · text-generation 15.7 B 164 K other 304 K from 37.4 GB
284 SmolLM2-360M-Instruct HuggingFaceTB · text-generation 360 M 8 K ✓ apache-2.0 303 K from 1.4 GB
285 Qwen2-0.5B-Instruct Qwen · text-generation 490 M 33 K ✓ apache-2.0 302 K from 1.7 GB
286 supergemma4-26b-uncensored-gguf-v2 Jiunsong · text-generation — — ⚠ gemma 301 K from 19.0 GB
287 Olmo-3-7B-Instruct allenai · text-generation 7.3 B 66 K ✓ apache-2.0 300 K from 17.7 GB
288 Qwen2.5-14B-bnb-4bit unsloth · text-generation 15.2 B 131 K ✓ apache-2.0 298 K from 13.7 GB
289 Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF Jackrong · text-generation — — ✓ apache-2.0 297 K from 2.5 GB
290 Qwopus-GLM-18B-Merged-GGUF KyleHessling1 · text-generation — — ✓ apache-2.0 295 K from 9.2 GB
291 Qwen3-0.6B-GGUF MaziyarPanahi · text-generation — — unknown 295 K from 0.9 GB
292 DeepSeek-R1-0528-Qwen3-8B-MLX-4bit lmstudio-community · text-generation 1.3 B 131 K ✓ mit 293 K from 5.8 GB
293 Qwen2.5-7B-Instruct unsloth · text-generation 7.6 B 33 K ✓ apache-2.0 292 K from 18.4 GB
294 deepseek-coder-6.7b-instruct deepseek-ai · text-generation 6.7 B 16 K other 292 K from 16.3 GB
295 Qwen2.5-3B-Instruct-GGUF Qwen · text-generation — — other 286 K from 2.0 GB
296 MiMo-V2.5 XiaomiMiMo · text-generation 310.8 B 1.0 M ✓ mit 286 K from 394.4 GB
297 Qwen3.8-Flash-Next-GGUF AtomicChat · text-generation — — other 285 K from 1.5 GB
298 Jan-v3.5-4B-gguf janhq · text-generation — — ✓ apache-2.0 284 K from 2.8 GB
299 Llama-3.2-1B-Instruct-FP8-dynamic RedHatAI · text-generation 1.5 B 131 K ⚠ llama3.2 283 K from 3.0 GB
300 Ornith-1.5-9B-MLX-4bit ornith-ai · text-generation 9.0 B — unknown 283 K from 7.4 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.