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 88 image-text-to-text 80 sentence-similarity 55 feature-extraction 45 translation 43 text-classification 39 image-classification 32 token-classification 21 text-to-speech 12 audio-classification 10 object-detection 10 image-segmentation 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
201 Laguna-S-2.1-NVFP4 poolside · text-generation 117.6 B 1.0 M openmdw-1.1 436 K from 127.8 GB
202 DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai · text-generation 1.8 B 131 K ✓ mit 431 K from 4.7 GB
203 Qwen3-4B-GGUF Qwen · text-generation — — ✓ apache-2.0 428 K from 3.2 GB
204 Qwen2.5-3B-Instruct-AWQ Qwen · text-generation 3.4 B 33 K other 427 K from 4.0 GB
205 Ornith-1.0-35B-FP8 protoLabsAI · text-generation 35.1 B — ✓ mit 425 K from 47.1 GB
206 maple-preview-GGUF deepgrove · text-generation — — ✓ mit 424 K from 6.5 GB
207 Qwen-AgentWorld-35B-A3B-GGUF unsloth · text-generation — — ✓ apache-2.0 423 K from 13.1 GB
208 MiniCPM5-2B openbmb · text-generation 2.5 B 131 K ✓ apache-2.0 421 K from 6.4 GB
209 Qwen3-4B-Thinking-2507 Qwen · text-generation 4.0 B 262 K ✓ apache-2.0 420 K from 10.0 GB
210 Qwen3.6-14B-A3B-FableVibes-GGUF tvall43 · text-generation — — ✓ apache-2.0 419 K from 6.4 GB
211 Mistral-7B-v0.1 mistralai · text-generation 7.2 B 33 K ✓ apache-2.0 415 K from 17.5 GB
212 saiga_llama3_8b IlyaGusev · text-generation 8.0 B 8 K other 414 K from 19.4 GB
213 GPT-OSS-20B-NPU2 FastFlowLM · text-generation 20.0 B 131 K ✓ apache-2.0 411 K from 47.5 GB
214 Ornith-1.5-35B-A3B ornith-ai · text-generation 36.0 B — ✓ mit 410 K from 85.0 GB
215 NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 nvidia · text-generation 31.6 B 262 K other 409 K from 41.2 GB
216 Phi-3-mini-4k-instruct microsoft · text-generation 3.8 B 4 K ✓ mit 407 K from 9.5 GB
217 Qwen3-8B-GGUF Qwen · text-generation — — ✓ apache-2.0 404 K from 6.0 GB
218 gemma-2-9b-it-AWQ-INT4 hugging-quants · text-generation 9.2 B 8 K ⚠ gemma 402 K from 8.7 GB
219 Qwen2.5-VL-7B-Instruct-NVFP4 nvidia · text-generation 5.0 B 128 K other 399 K from 9.2 GB
220 EXAONE-3.5-7.8B-Instruct LGAI-EXAONE · text-generation 7.8 B 33 K other 396 K from 36.1 GB
221 gemma-3-270m google · text-generation · gated 270 M — ⚠ gemma 395 K from 1.1 GB
222 granite-4.1-3b ibm-granite · text-generation 3.4 B 131 K ✓ apache-2.0 393 K from 8.5 GB
223 Ternary-Bonsai-8B-gguf prism-ml · text-generation — — ✓ apache-2.0 392 K from 2.9 GB
224 Qwen3.8-27B-DFlash2 incoai · text-generation 1.9 B 262 K ✓ apache-2.0 391 K from 5.0 GB
225 Kwaipilot_KAT-Coder-V2.5-Dev-GGUF bartowski · text-generation — — ✓ apache-2.0 390 K from 11.3 GB
226 Ornith-1.0-397B deepreinforce-ai · text-generation 396.8 B — ✓ mit 387 K from 933.0 GB
227 Phi-4-mini-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 384 K from 9.5 GB
228 TwIL-LM3 webAI-Official · text-generation 3.1 B 66 K other 384 K from 3.1 GB
229 NVIDIA-Nemotron-Nano-9B-v2 nvidia · text-generation 8.9 B 131 K other 383 K from 21.4 GB
230 Ornith-1.5-35B-A3B-MLX ornith-ai · text-generation 34.7 B — unknown 383 K from 82.0 GB
231 Ornith-1.5-397B-FP8 ornith-ai · text-generation 403.4 B — ✓ mit 382 K from 521.2 GB
232 falcon-7b tiiuae · text-generation 7.2 B — ✓ apache-2.0 379 K from 17.5 GB
233 pythia-14m EleutherAI · text-generation 10 M 2 K ✓ apache-2.0 378 K from 0.5 GB
234 Hermes-3-Llama-3.1-8B NousResearch · text-generation 8.0 B 131 K ⚠ llama3 377 K from 19.4 GB
235 mistral-7b-v0.3-bnb-4bit unsloth · text-generation 7.5 B 33 K ✓ apache-2.0 377 K from 6.2 GB
236 Qwen3-235B-A22B-Instruct-2507-FP8 Qwen · text-generation 235.1 B 262 K ✓ apache-2.0 376 K from 295.8 GB
237 Ornith-1.5-9B-OBLITERATED OBLITERATUS · text-generation 9.7 B — ✓ mit 371 K from 6.3 GB
238 Qwen2-7B-Instruct Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 369 K from 18.4 GB
239 Llama-3.2-3B meta-llama · text-generation · gated 3.2 B — ⚠ llama3.2 368 K from 8.0 GB
240 Parable-Granite-4.1-3B-Claude-Fable-5-GGUF AnkitAI · text-generation — — ✓ apache-2.0 366 K from 2.8 GB
241 Qwen3.8-27B-DFlash2 z-lab · text-generation 1.9 B 262 K ✓ apache-2.0 364 K from 5.0 GB
242 Parable-Granite-4.1-8B-Claude-Fable-5-GGUF AnkitAI · text-generation — — ✓ apache-2.0 362 K from 6.1 GB
243 Qwen2.5-Coder-1.5B Qwen · text-generation 1.5 B 33 K ✓ apache-2.0 361 K from 4.1 GB
244 MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF GnLOLot · text-generation — — ✓ apache-2.0 360 K from 1.8 GB
245 Qwen3.6-35B-A3B-NVFP4-MTP-GGUF michaelw9999 · text-generation — — unknown 360 K from 23.0 GB
246 POCKET-26B-GGUF FINAL-Bench · text-generation — — ✓ apache-2.0 360 K from 12.7 GB
247 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8 RedHatAI · text-generation 31.6 B 262 K unknown 357 K from 40.8 GB
248 Qwen2.5-72B-Instruct Qwen · text-generation 72.7 B 33 K other 356 K from 171.4 GB
249 vlt5-base-keywords Voicelab · text-generation 280 M — ✓ cc-by-4.0 355 K from 1.8 GB
250 Ornith-1.0-397B-FP8 ornith-ai · text-generation 396.8 B — ✓ mit 354 K from 505.7 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.