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
151 DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai · text-generation 1.8 B 131 K ✓ mit 619 K from 4.7 GB
152 OLMo-2-0425-1B allenai · text-generation 1.5 B 4 K ✓ apache-2.0 618 K from 7.3 GB
153 NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 nvidia · text-generation 31.6 B 262 K other 613 K from 41.2 GB
154 Qwen2-7B-Instruct Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 606 K from 18.4 GB
155 Qwen2.5-Coder-7B-Instruct-AWQ Orion-zhen · text-generation 7.6 B 33 K ✓ apache-2.0 604 K from 7.9 GB
156 VLM2Vec-Full TIGER-Lab · text-generation 4.2 B 131 K ✓ apache-2.0 599 K from 10.2 GB
157 deepseek-coder-7b-instruct-v1.5 deepseek-ai · text-generation 6.9 B 4 K other 599 K from 16.7 GB
158 Qwen3-30B-A3B-Instruct-2507-FP8 Qwen · text-generation 30.5 B 262 K ✓ apache-2.0 588 K from 39.4 GB
159 LFM2.5-1.2B-Instruct LiquidAI · text-generation 1.2 B 128 K other 584 K from 3.3 GB
160 Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit cyankiwi · text-generation 5.3 B 262 K ✓ apache-2.0 583 K from 21.2 GB
161 gemma-2-2b-it google · text-generation · gated 2.6 B — ⚠ gemma 576 K from 6.6 GB
162 gpt2-medium openai-community · text-generation 380 M — ✓ mit 572 K from 2.2 GB
163 gpt-oss-20b-GGUF unsloth · text-generation — 131 K ✓ apache-2.0 560 K from 13.1 GB
164 Hermes-3-Llama-3.1-8B NousResearch · text-generation 8.0 B 131 K ⚠ llama3 558 K from 19.4 GB
165 DeepSeek-Coder-V2-Lite-Instruct deepseek-ai · text-generation 15.7 B 164 K other 557 K from 37.4 GB
166 MiniMax-M3-NVFP4 nvidia · text-generation 246.6 B — other 557 K from 312.6 GB
167 Qwen3-Coder-Next Qwen · text-generation 79.7 B 262 K ✓ apache-2.0 554 K from 187.7 GB
168 deepseek-coder-6.7b-instruct deepseek-ai · text-generation 6.7 B 16 K other 553 K from 16.3 GB
169 Llama-3.2-3B meta-llama · text-generation · gated 3.2 B — ⚠ llama3.2 552 K from 8.0 GB
170 MiMo-7B-RL XiaomiMiMo · text-generation 7.8 B 33 K ✓ mit 552 K from 18.9 GB
171 Phi-3-mini-4k-instruct microsoft · text-generation 3.8 B 4 K ✓ mit 544 K from 9.5 GB
172 macbert4csc-base-chinese shibing624 · text-generation 100 M 512 ✓ apache-2.0 542 K from 1.0 GB
173 Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 536 K from 7.8 GB
174 Qwen-AgentWorld-35B-A3B-GGUF unsloth · text-generation — — ✓ apache-2.0 534 K from 13.1 GB
175 Qwen2.5-Coder-7B-Instruct-AWQ Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 522 K from 7.8 GB
176 DeepSeek-V4-Flash-DSpark deepseek-ai · text-generation 165.3 B 1.0 M ✓ mit 519 K from 208.9 GB
177 EXAONE-3.5-7.8B-Instruct LGAI-EXAONE · text-generation 7.8 B 33 K other 518 K from 36.1 GB
178 DeepSeek-R1-Distill-Llama-70B deepseek-ai · text-generation 70.6 B 131 K ✓ mit 512 K from 166.3 GB
179 gemma-2-9b-it-AWQ-INT4 hugging-quants · text-generation 9.2 B 8 K ⚠ gemma 504 K from 8.7 GB
180 DeepSeek-V2-Lite deepseek-ai · text-generation 15.7 B 164 K other 503 K from 37.4 GB
181 t5gemma-s-s-prefixlm google · text-generation · gated 310 M — ⚠ gemma 499 K from 1.2 GB
182 SmolLM2-360M-Instruct HuggingFaceTB · text-generation 360 M 8 K ✓ apache-2.0 494 K from 1.4 GB
183 Llama-3.1-405B-FP8 meta-llama · text-generation · gated 405.9 B — ⚠ llama3.1 493 K from 597.3 GB
184 GLM-5.1-FP8 zai-org · text-generation 753.9 B 203 K ✓ mit 493 K from 945.4 GB
185 Qwen2.5-32B-Instruct-GPTQ-Int4 Qwen · text-generation 32.8 B 33 K ✓ apache-2.0 492 K from 26.7 GB
186 tiny-mixtral TitanML · text-generation 250 M 131 K unknown 490 K from 1.6 GB
187 GLM-4.7-Flash-AWQ-4bit cyankiwi · text-generation 32.1 B 203 K ✓ mit 489 K from 27.5 GB
188 Meta-Llama-3.1-8B-Instruct-FP8 RedHatAI · text-generation 8.0 B 131 K ⚠ llama3.1 479 K from 11.7 GB
189 NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 nvidia · text-generation 560.5 B 262 K other 469 K from 1,317.7 GB
190 typhoon2.5-qwen3-4b typhoon-ai · text-generation 4.0 B 262 K ✓ apache-2.0 468 K from 10.0 GB
191 Bielik-11B-v3.0-Instruct speakleash · text-generation · gated 11.2 B — ✓ apache-2.0 464 K from 26.7 GB
192 Llama-3.3-70B-Instruct meta-llama · text-generation · gated 70.6 B — ⚠ llama3.3 464 K from 166.3 GB
193 Qwen3-4B-AWQ Qwen · text-generation 4.0 B 41 K ✓ apache-2.0 463 K from 4.0 GB
194 Qwen3-30B-A3B-abliterated mlabonne · text-generation 30.5 B 41 K ✓ apache-2.0 459 K from 206.6 GB
195 Bonsai-27B-mlx-1bit prism-ml · text-generation 1.7 B — ✓ apache-2.0 457 K from 6.4 GB
196 Phi-4-mini-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 455 K from 9.5 GB
197 Ternary-Bonsai-27B-mlx-2bit prism-ml · text-generation 2.6 B — ✓ apache-2.0 453 K from 10.2 GB
198 xlnet-base-cased xlnet · text-generation — — ✓ mit 452 K —
199 Qwen3-8B-Base Qwen · text-generation 8.2 B 33 K ✓ apache-2.0 451 K from 19.7 GB
200 Qwen2.5-3B-Instruct-unsloth-bnb-4bit unsloth · text-generation 3.2 B 33 K ✓ apache-2.0 449 K from 3.6 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.