AImodelsComparison.com 1,213 open · 210 API
Menu
Models Best of Trending Can I run it? Methodology MCP server About
1,213 models · 1,213 open weights · 210 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 1,423 Open weights (self-host) 1,213 API-only 210
Task
All text-generation 539 text-to-image 155 image-text-to-text 110 ASR 82 sentence-similarity 63 text-classification 50 translation 50 feature-extraction 46 image-classification 41 token-classification 22 text-to-speech 19 summarization 9 audio-classification 9 image-segmentation 9 object-detection 7 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
$
871 models
#ModelParamsContextCommercial use30dOn Mac M4 Max · 64 GB
251 nb-wav2vec2-1b-bokmaal-v2 NbAiLab · ASR Open weights 960 M — ✓ apache-2.0 947 K 4.9 GB
252 Ornith-1.0-35B-FP8 deepreinforce-ai · text-generation Open weights 35.1 B — ✓ mit 945 K 47.2 GB
253 TinyLlama-1.1B-Chat-v1.0 TinyLlama · text-generation Open weights 1.1 B 2 K ✓ apache-2.0 944 K 3.1 GB
254 PP-DocLayoutV3_safetensors PaddlePaddle · object-detection Open weights 33 M — ✓ apache-2.0 937 K 0.7 GB
255 Wav2Vec2-large-xlsr-hindi theainerd · ASR Open weights 316 M — unknown 932 K 1.9 GB
256 nllb-200-distilled-600M facebook · translation Open weights 600 M 1 K ✗ cc-by-nc-4.0 932 K 1.9 GB
257 Qwen3.8-27B-AP-GGUF agentionai · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 923 K 15.1 GB
258 ThinkingCap-Qwen3.8-27B-GGUF bottlecapai · image-text-to-text Open weights 27.0 B — other 923 K 21.6 GB
259 Qwen2.5-32B-Instruct-AWQ Qwen · text-generation Open weights 32.8 B 33 K ✓ apache-2.0 923 K 26.7 GB
260 paraphrase-MiniLM-L3-v2 sentence-transformers · sentence-similarity Open weights 20 M 512 ✓ apache-2.0 919 K 0.6 GB
261 Qwen-Image-2.1-FP8 unsloth · text-to-image Open weights 7.1 B — other 915 K 46.7 GB
262 gpt2-large openai-community · text-generation Open weights 810 M — ✓ mit 908 K 4.2 GB
263 llmlingua-2-bert-base-multilingual-cased-meetingbank microsoft · token-classification Open weights 180 M 512 ✓ apache-2.0 905 K 1.3 GB
264 dreamshaper-7 Lykon · text-to-image Open weights 860 M — ⚠ creativeml-openrail-m 902 K 9.7 GB
265 JiRackUltra_1b CMSManhattan · text-generation Open weights 1.8 B 131 K ✓ mit 891 K 1.8 GB
266 wav2vec2-xls-r-300m-ftspeech saattrupdan · ASR Open weights 320 M — other 888 K 1.9 GB
267 gte-multilingual-base Alibaba-NLP · sentence-similarity Open weights 310 M 8 K ✓ apache-2.0 883 K 1.2 GB
268 LFM2.5-24B-A2B-Turbo-Brilliance-50X-NEO-MAX-Imatrix-GGUF DavidAU · text-generation Open weights 24.0 B 131 K other 881 K 15.7 GB
269 distiluse-base-multilingual-cased-v2 sentence-transformers · sentence-similarity Open weights 130 M 512 ✓ apache-2.0 879 K 1.1 GB
270 Sharp-Spark-X2.5-4B-GGUF peculiar-ragdoll · text-generation Open weights 4.0 B — ✓ apache-2.0 874 K 1.1 GB
271 Llama-3.2-3B-Instruct meta-llama · text-generation · gated Open weights Also via API 3.2 B — ⚠ llama3.2 872 K 8.0 GB
272 stsb-bert-tiny-safetensors sentence-transformers-testing · sentence-similarity Open weights <0.1 M 512 unknown 860 K 0.5 GB
273 rorshark-vit-base amunchet · image-classification Open weights 90 M — ✓ apache-2.0 860 K 0.9 GB
274 text2vec-base-chinese shibing624 · sentence-similarity Open weights 100 M 512 ✓ apache-2.0 855 K 1.0 GB
275 bge-small-en-v1.5 Xenova · feature-extraction Open weights 30 M 512 unknown 855 K 0.6 GB
276 pubmedbert-base-embeddings NeuML · sentence-similarity Open weights 110 M 512 ✓ apache-2.0 848 K 1.0 GB
277 SmolLM2-135M-Instruct HuggingFaceTB · text-generation Open weights 130 M 8 K ✓ apache-2.0 847 K 0.8 GB
278 w2v-xls-r-uk Yehor · ASR Open weights 320 M — ✓ apache-2.0 844 K 1.9 GB
279 Qwen3-TTS-12Hz-0.6B-Base Qwen · text-to-speech Open weights 910 M — ✓ apache-2.0 842 K 3.4 GB
280 nomic-embed-text-v1 nomic-ai · sentence-similarity Open weights 140 M 8 K ✓ apache-2.0 836 K 1.1 GB
281 wav2vec2-large-xlsr-53-gender-recognition-librispeech alefiury · audio-classification Open weights 320 M — ✓ apache-2.0 835 K 1.9 GB
282 Qwen3-8B-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 826 K 6.0 GB
283 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8 RedHatAI · text-generation Open weights 31.6 B 262 K unknown 820 K 40.8 GB
284 parakeet-tdt-0.6b-v2 mlx-community · ASR Open weights 620 M — ✓ cc-by-4.0 815 K 3.3 GB
285 Ornith-1.0-9B ornith-ai · text-generation Open weights <0.1 M — ✓ mit 814 K 21.2 GB
286 repeat unslothai · feature-extraction Open weights — — unknown 812 K 0.5 GB
287 Kokoro-82M-v1.0-ONNX onnx-community · text-to-speech Open weights 82 M — ✓ apache-2.0 808 K 0.7 GB
288 gemma-2-9b-it-AWQ-INT4 hugging-quants · text-generation Open weights 9.2 B 8 K ⚠ gemma 803 K 8.7 GB
289 distilbert-base-multilingual-cased-sentiments-student lxyuan · text-classification Open weights 140 M 512 ✓ apache-2.0 795 K 1.1 GB
290 wide_resnet50_2.racm_in1k timm · image-classification Open weights 70 M — ✓ apache-2.0 795 K 0.8 GB
291 wav2vec2-xls-r-300m-sk-cv8 comodoro · ASR Open weights 300 M — ✓ apache-2.0 786 K 1.2 GB
292 nb-wav2vec2-1b-nynorsk NbAiLab · ASR Open weights 960 M — ✓ apache-2.0 775 K 4.9 GB
293 Qwen2.5-Coder-7B-Instruct-AWQ Qwen · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 769 K 7.8 GB
294 Qwen-Image-2.1-Turbo-Uncensored-GGUF AtomicChat · text-to-image Open weights 8.8 B — ✓ apache-2.0 761 K 5.5 GB
295 ruri-v3-310m cl-nagoya · sentence-similarity Open weights 310 M 8 K ✓ apache-2.0 759 K 1.9 GB
296 yolos-small hustvl · object-detection Open weights 30 M — ✓ apache-2.0 751 K 0.6 GB
297 distil-large-v3 distil-whisper · ASR Open weights 760 M — ✓ mit 747 K 5.6 GB
298 Qwen2.5-7B-Instruct-GGUF Qwen · text-generation Open weights 7.0 B 33 K ✓ apache-2.0 738 K 4.9 GB
299 Qwen2.5-Math-PRM-7B Qwen · text-classification Open weights 7.6 B 4 K other 738 K 18.4 GB
300 e5-large-v2 intfloat · sentence-similarity Open weights 340 M 512 ✓ mit 737 K 2.0 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.