AImodelsComparison.com 1,226 open · 200 API
Menu
Models Best of Trending Can I run it? Methodology About
1,226 models · 1,226 open weights · 200 API-only · refreshed nightly

Open-weights models

Models whose weights are published on Hugging Face — download them and run them on your own hardware. Many are also served by hosted providers; those carry an "Also via API" badge with live prices.

Type
All 1,426 Open weights (self-host) 1,226 API-only 200
Task
All text-generation 534 text-to-image 155 image-text-to-text 112 ASR 86 sentence-similarity 64 translation 56 text-classification 51 feature-extraction 48 image-classification 39 token-classification 21 text-to-speech 19 audio-classification 12 image-segmentation 11 summarization 8 object-detection 8 audio-text-to-text 1 any-to-any 1
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
$
534 models
#ModelParamsContextCommercial use30dMin VRAM
151 Qwen3-4B-GGUF unsloth · text-generation Open weights — 41 K ✓ apache-2.0 495 K from 2.3 GB
152 JiRackDeltaNet_27b CMSManhattan · text-generation Open weights 27.3 B 262 K ✓ mit 494 K from 16.5 GB
153 orcarouter_GLM-5.3-Flash-Uncensored-GGUF BoldingBuilds · text-generation Open weights 321.3 B — ✓ mit 492 K from 49.9 GB
154 Meta-Llama-3.1-8B-Instruct-GGUF bartowski · text-generation Open weights — — ⚠ llama3.1 489 K from 3.7 GB
155 Olmo-3-7B-Think allenai · text-generation Open weights 7.3 B 66 K ✓ apache-2.0 488 K from 17.7 GB
156 Qwen2.5-32B-Instruct-GPTQ-Int4 Qwen · text-generation Open weights 32.8 B 33 K ✓ apache-2.0 486 K from 26.7 GB
157 Qwen3-8B-FP8 Qwen · text-generation Open weights 8.2 B 41 K ✓ apache-2.0 482 K from 12.1 GB
158 Qwen3-VL-30B-A3B-Instruct-AWQ QuantTrio · text-generation Open weights 31.1 B — ✓ apache-2.0 474 K from 24.8 GB
159 Qwen2.5-Coder-7B-Instruct-AWQ Orion-zhen · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 468 K from 7.9 GB
160 gpt-neo-125m EleutherAI · text-generation Open weights 150 M 2 K ✓ mit 463 K from 1.1 GB
161 Llama-2-7b-hf meta-llama · text-generation · gated Open weights 6.7 B — ⚠ llama2 462 K from 16.3 GB
162 Qwen3.8-2B-Distill-GGUF empero-ai · text-generation Open weights — — ✓ apache-2.0 462 K from 1.9 GB
163 Hermes-3-Llama-3.1-8B NousResearch · text-generation Open weights 8.0 B 131 K ⚠ llama3 460 K from 19.4 GB
164 Apodex-1.1-mini-GGUF abenzerps · text-generation Open weights — — ✓ apache-2.0 457 K from 10.2 GB
165 Qwen3-Coder-30B-A3B-Instruct-GGUF unsloth · text-generation Open weights — — ✓ apache-2.0 456 K from 12.9 GB
166 Ornith-1.5-9B ornith-ai · text-generation Open weights 9.7 B — ✓ mit 455 K from 23.2 GB
167 Llama-3.1-405B-FP8 meta-llama · text-generation · gated Open weights 405.9 B — ⚠ llama3.1 455 K from 597.3 GB
168 Qwen2.5-72B-Instruct-AWQ Qwen · text-generation Open weights 73.0 B 33 K other 453 K from 57.2 GB
169 Qwen3.6-35B-A3B-abliterated-v4 Bahushruth · text-generation Open weights 34.7 B 262 K ✓ apache-2.0 447 K from 82.0 GB
170 GLM-4.7-Flash-AWQ QuantTrio · text-generation Open weights 31.2 B 203 K ✓ mit 447 K from 26.9 GB
171 MiniMax-M2.7 MiniMaxAI · text-generation Open weights Also via API 228.7 B 205 K other 439 K from 288.0 GB
172 Qwen2.5-Coder-3B-Instruct Qwen · text-generation Open weights 3.1 B 33 K other 439 K from 7.8 GB
173 phi-2 microsoft · text-generation Open weights 2.8 B 2 K ✓ mit 433 K from 7.0 GB
174 Ornith-1.5-397B-NVFP4 ornith-ai · text-generation Open weights 397.0 B — ✓ mit 433 K from 411.4 GB
175 maple-preview-GGUF deepgrove · text-generation Open weights — — ✓ mit 424 K from 6.5 GB
176 DeepSeek-Coder-V2-Lite-Instruct deepseek-ai · text-generation Open weights 15.7 B 164 K other 424 K from 37.4 GB
177 deepseek-coder-7b-instruct-v1.5 deepseek-ai · text-generation Open weights 6.9 B 4 K other 421 K from 16.7 GB
178 Apertus-8B-Instruct-2509 swiss-ai · text-generation Open weights 8.1 B 66 K ✓ apache-2.0 416 K from 19.4 GB
179 Laguna-S-2.1 poolside · text-generation Open weights Also via API 117.6 B 1.0 M openmdw-1.1 414 K from 276.8 GB
180 pythia-6.9b EleutherAI · text-generation Open weights 7.0 B 2 K ✓ apache-2.0 414 K from 16.8 GB
181 Qwen3-30B-A3B-Instruct-2507-AWQ stelterlab · text-generation Open weights 30.8 B 262 K ✓ apache-2.0 411 K from 23.5 GB
182 gemma-2-9b-it google · text-generation · gated Open weights 9.2 B — ⚠ gemma 409 K from 22.2 GB
183 Qwen3-235B-A22B Qwen · text-generation Open weights 235.1 B 41 K ✓ apache-2.0 406 K from 553.0 GB
184 Qwen2.5-Coder-1.5B-Instruct Qwen · text-generation Open weights 1.5 B 33 K ✓ apache-2.0 404 K from 4.1 GB
185 saiga_llama3_8b IlyaGusev · text-generation Open weights 8.0 B 8 K other 390 K from 19.4 GB
186 GPT-OSS-20B-NPU2 FastFlowLM · text-generation Open weights 20.0 B 131 K ✓ apache-2.0 390 K from 47.5 GB
187 Ornith-1.0-397B deepreinforce-ai · text-generation Open weights 396.8 B — ✓ mit 387 K from 933.0 GB
188 Qwen3.8-27B-MTP-NVFP4 sakamakismile · text-generation Open weights 27.4 B — ✓ apache-2.0 383 K from 27.2 GB
189 japanese-gpt-neox-small rinna · text-generation Open weights 200 M 2 K ✓ mit 381 K from 1.3 GB
190 Spark-X2.5-4B-GGUF XHToken · text-generation Open weights 4.0 B — ✓ apache-2.0 380 K from 4.0 GB
191 Qwen2.5-Coder-1.5B Qwen · text-generation Open weights 1.5 B 33 K ✓ apache-2.0 376 K from 4.1 GB
192 GLM-5.3-GGUF unsloth · text-generation Open weights — — other 373 K from 52.0 GB
193 Meta-Llama-3-8B-Instruct meta-llama · text-generation · gated Open weights 8.0 B — ⚠ llama3 372 K from 19.4 GB
194 Ling-3.0-tiny-MLX-4bit rapid-mlx · text-generation Open weights 7.9 B 131 K ✓ mit 372 K from 6.6 GB
195 gemma-4-31B-it-qat-NVFP4-Blackwell melcheikh · text-generation Open weights 31.0 B — ✓ apache-2.0 371 K from 27.6 GB
196 Phi-3.5-mini-instruct microsoft · text-generation Open weights 3.8 B 131 K ✓ mit 365 K from 9.5 GB
197 DeepSeek-R1-0528-Qwen3-8B deepseek-ai · text-generation Open weights 8.2 B 131 K ✓ mit 363 K from 19.7 GB
198 Qwen3.8-27B-DFlash2 incoai · text-generation Open weights 1.9 B 262 K ✓ apache-2.0 362 K from 5.0 GB
199 mistral-7b-v0.3-bnb-4bit unsloth · text-generation Open weights 7.5 B 33 K ✓ apache-2.0 361 K from 6.2 GB
200 Qwen3-Coder-480B-A35B-Instruct-FP8 Qwen · text-generation Open weights 480.2 B 262 K ✓ apache-2.0 357 K from 602.9 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.