AImodelsComparison.com 1,000 models
Menu
Models Best of Trending Can I run it? Methodology About
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.

Task
All text-generation 400 text-to-image 150 ASR 85 image-text-to-text 80 sentence-similarity 54 feature-extraction 46 translation 43 text-classification 39 image-classification 32 token-classification 21 text-to-speech 15 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
301 Phi-3-vision-128k-instruct microsoft · text-generation 4.2 B 131 K ✓ mit 231 K from 10.2 GB
302 Nemotron-Labs-Diffusion-8B nvidia · text-generation 8.5 B 262 K other 228 K from 20.6 GB
303 TinyLLama-v0 Maykeye · text-generation 0 M 2 K ✓ apache-2.0 226 K from 0.5 GB
304 LFM2.5-1.2B-Instruct-GGUF LiquidAI · text-generation — — other 226 K from 1.3 GB
305 Qwen2.5-14B-bnb-4bit unsloth · text-generation 15.2 B 131 K ✓ apache-2.0 224 K from 13.7 GB
306 Qwen3.6-35B-A3B-DFlash z-lab · text-generation 390 M 262 K ✓ apache-2.0 224 K from 1.4 GB
307 Qwen3-4B-GGUF MaziyarPanahi · text-generation — — unknown 223 K from 2.3 GB
308 vlt5-base-keywords Voicelab · text-generation 280 M — ✓ cc-by-4.0 223 K from 1.8 GB
309 gemma-4-12b-heretic-abliterated-GGUF culturerevolt · text-generation — — ✓ apache-2.0 219 K from 0.7 GB
310 NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 nvidia · text-generation 335.0 B 262 K other 219 K from 438.3 GB
311 lynx-instruct-30b bineric · text-generation 30.5 B 262 K ✓ apache-2.0 218 K from 72.3 GB
312 Gemma-4-E4B-DECKARD-HERETIC-NVFP4 AEON-7 · text-generation 6.2 B — ⚠ gemma 217 K from 12.6 GB
313 Meta-Llama-3.1-8B-FP8 RedHatAI · text-generation 8.0 B 131 K ⚠ llama3.1 216 K from 11.7 GB
314 Mistral-7B-Instruct-v0.1 mistralai · text-generation 7.2 B 33 K ✓ apache-2.0 216 K from 17.5 GB
315 DeepSeek-V3.2-Exp deepseek-ai · text-generation 685.4 B 164 K ✓ mit 214 K from 861.7 GB
316 GLM-4.7-Flash-AWQ QuantTrio · text-generation 31.2 B 203 K ✓ mit 214 K from 26.9 GB
317 SmolLM2-1.7B-Instruct HuggingFaceTB · text-generation 1.7 B 8 K ✓ apache-2.0 213 K from 4.5 GB
318 Mistral-7B-Instruct-v0.3-AWQ solidrust · text-generation 7.3 B 33 K ✓ apache-2.0 212 K from 6.2 GB
319 GLM-4.7-Flash-MLX-8bit lmstudio-community · text-generation 29.9 B 203 K ✓ mit 209 K from 40.0 GB
320 Llama-2-13b-chat-hf meta-llama · text-generation · gated 13.0 B — ⚠ llama2 207 K from 31.1 GB
321 Meta-Llama-3.1-70B-Instruct-AWQ-INT4 hugging-quants · text-generation 70.6 B 131 K ⚠ llama3.1 204 K from 54.8 GB
322 Ornith-1.0-35B-GGUF unsloth · text-generation — — ✓ mit 203 K from 12.1 GB
323 xflux_text_encoders XLabs-AI · text-generation 4.8 B — ✓ apache-2.0 203 K from 11.7 GB
324 DeepSeek-R1-0528 deepseek-ai · text-generation 684.5 B 164 K ✓ mit 202 K from 860.6 GB
325 Dolphin-Mistral-24B-Venice-Edition dphn · text-generation 24.0 B — ✓ apache-2.0 201 K from 56.9 GB
326 Qwen2.5-Coder-1.5B Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 200 K from 4.1 GB
327 gemma-1.1-2b-it google · text-generation · gated 2.5 B — ⚠ gemma 200 K from 6.4 GB
328 DeepSeek-Coder-V2-Lite-Instruct-FP8 RedHatAI · text-generation 15.7 B 164 K other 200 K from 20.6 GB
329 Qwen2.5-1.5B-Instruct-GGUF Qwen · text-generation — — ✓ apache-2.0 199 K from 1.3 GB
330 Qwen3-Coder-Next-GGUF unsloth · text-generation — — ✓ apache-2.0 199 K from 47.4 GB
331 Qwen1.5-0.5B-Chat Qwen · text-generation 620 M 33 K other 199 K from 2.0 GB
332 aya-expanse-8b-AWQ Orion-zhen · text-generation 9.1 B 8 K gpl-3.0 198 K from 10.5 GB
333 Qwen3-4B-Thinking-2507-FP8 Qwen · text-generation 4.4 B 262 K ✓ apache-2.0 197 K from 6.9 GB
334 Qwen2.5-Coder-32B-Instruct-GGUF Qwen · text-generation — — ✓ apache-2.0 197 K from 9.1 GB
335 NVIDIA-Nemotron-3-Super-120B-A12B-FP8 nvidia · text-generation 123.6 B 262 K other 197 K from 160.2 GB
336 PowerLM-3b ibm-research · text-generation 3.5 B 4 K ✓ apache-2.0 195 K from 16.5 GB
337 Kimi-K2.7-Code-NVFP4 decart-ai · text-generation — — other 194 K from 655.2 GB
338 GLM-4.7-Flash-MLX-6bit lmstudio-community · text-generation 29.9 B 203 K ✓ mit 194 K from 31.8 GB
339 Qwen1.5-MoE-A2.7B Qwen · text-generation 14.3 B 8 K other 193 K from 34.1 GB
340 OLMoE-1B-7B-0924 allenai · text-generation 6.9 B 4 K ✓ apache-2.0 192 K from 16.8 GB
341 talkie-1930-13b-it-hf lewtun · text-generation 13.3 B 2 K ✓ apache-2.0 191 K from 31.7 GB
342 pythia-160m-deduped EleutherAI · text-generation 210 M 2 K ✓ apache-2.0 191 K from 0.9 GB
343 DialoGPT-medium microsoft · text-generation — — ✓ mit 190 K —
344 Qwen2.5-Coder-7B-Instruct-GGUF Qwen · text-generation — — ✓ apache-2.0 189 K from 3.8 GB
345 Llama-3.2-3B-Instruct unsloth · text-generation 3.2 B 131 K ⚠ llama3.2 188 K from 8.0 GB
346 gemma4-e4b-claims-comparison k-chirkunov · text-generation · gated 7.9 B — ⚠ gemma 188 K from 19.2 GB
347 Phi-mini-MoE-instruct microsoft · text-generation 7.7 B 4 K ✓ mit 186 K from 18.5 GB
348 Qwen3-0.6B-GGUF MaziyarPanahi · text-generation — — unknown 186 K from 0.9 GB
349 Laguna-S-2.1-INT4 poolside · text-generation — — unknown 185 K —
350 Laguna-S-2.1-GGUF unsloth · text-generation — — openmdw-1.1 185 K from 37.6 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.