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
$
680 models
#ModelParamsContextCommercial use30dOn Mac M3 · 24 GB
251 Qwen2.5-32B-Instruct-GGUF bartowski · text-generation Open weights 32.0 B 33 K ✓ apache-2.0 676 K 15.2 GB
252 wav2vec2-xls-r-300m-bengali arijitx · ASR Open weights 300 M — ✓ apache-2.0 676 K 1.2 GB
253 nsfw-image-detection-384 Marqo · image-classification Open weights 5.6 M — ✓ apache-2.0 674 K 0.5 GB
254 whisper-large-v3-turbo-gguf handy-computer · ASR Open weights 810 M — ✓ mit 671 K 1.2 GB
255 Diplodocus-preview-GGUF OsaurusAI · text-generation Open weights — — ✓ apache-2.0 663 K 0.5 GB
256 whisper-medium-gguf handy-computer · ASR Open weights 760 M — ✓ apache-2.0 662 K 1.2 GB
257 noobai-XL-1.1 Laxhar · text-to-image Open weights 2.6 B — other 662 K 16.3 GB
258 multi-qa-MiniLM-L6-cos-v1 sentence-transformers · sentence-similarity Open weights 20 M 512 unknown 661 K 0.6 GB
259 convnext_tiny.in12k_ft_in1k timm · image-classification Open weights 30 M — ✓ apache-2.0 651 K 0.6 GB
260 whisper-tiny openai · ASR Open weights 40 M — ✓ apache-2.0 650 K 0.7 GB
261 wikineural-multilingual-ner Babelscape · token-classification Open weights 180 M 512 ✗ cc-by-nc-sa-4.0 649 K 1.3 GB
262 Qwen3-ASR-0.6B Qwen · ASR Open weights 940 M — ✓ apache-2.0 645 K 2.7 GB
263 LFM2.5-24B-A2B-Uncensored-GGUF AtomicChat · text-generation Open weights 24.0 B 131 K other 639 K 4.1 GB
264 MiniCPM5-2B-DSpark openbmb · text-generation Open weights 324 M 131 K ✓ apache-2.0 631 K 1.3 GB
265 Qwen3-1.7B-Base Qwen · text-generation Open weights 1.7 B 33 K ✓ apache-2.0 629 K 4.5 GB
266 gpt-oss-20b-GGUF unsloth · text-generation Open weights — 131 K ✓ apache-2.0 624 K 13.1 GB
267 MiniCPM-SALA-AWQ-8bit cyankiwi · text-generation Open weights 3.1 B 524 K ✓ apache-2.0 621 K 12.7 GB
268 embeddinggemma-300m-ONNX onnx-community · sentence-similarity Open weights 300 M 2 K ⚠ gemma 617 K 1.2 GB
269 Qwen3-0.6B-Base Qwen · text-generation Open weights 600 M 33 K ✓ apache-2.0 612 K 1.9 GB
270 all-roberta-large-v1 sentence-transformers · sentence-similarity Open weights 360 M 512 ✓ apache-2.0 612 K 2.1 GB
271 Qwen3-TTS-12Hz-1.7B-VoiceDesign Qwen · text-to-speech Open weights 1.9 B — ✓ apache-2.0 608 K 5.8 GB
272 repvgg_a0.rvgg_in1k timm · image-classification Open weights 10 M — ✓ mit 608 K 0.5 GB
273 deepseek-v4-gguf antirez · text-generation Open weights — — ✓ mit 606 K 4.7 GB
274 Spark-X2.6-4B-GGUF XHToken · text-generation Open weights 4.0 B — ✓ apache-2.0 606 K 5.0 GB
275 DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai · text-generation Open weights 1.8 B 131 K ✓ mit 600 K 4.7 GB
276 wav2vec2-large-xlsr-mvc-swahili eddiegulay · ASR Open weights 320 M — ✓ apache-2.0 600 K 1.9 GB
277 bloomz-560m bigscience · text-generation Open weights 560 M — ⚠ bigscience-bloom-rail-1.0 599 K 1.8 GB
278 bge-small-en-v1.5 michaelfeil · feature-extraction Open weights 30 M 512 ✓ mit 599 K 0.7 GB
279 wav2vec2-large-xls-r-300m-welsh infinitejoy · ASR Open weights 300 M — ✓ apache-2.0 591 K 1.2 GB
280 Qwen3.8-27B-Defiance-Uncensored-MTP-GGUF ttindall · text-generation Open weights 27.0 B — ✓ apache-2.0 590 K 5.5 GB
281 nomic-embed-text-v1.5-GGUF nomic-ai · sentence-similarity Open weights 140 M 2 K ✓ apache-2.0 587 K 0.6 GB
282 Sage-A1.5-Q4_K_M-GGUF InternScience · text-generation Open weights — — ✓ apache-2.0 586 K 1.5 GB
283 Juggernaut-XL-v9 RunDiffusion · text-to-image Open weights — — ⚠ creativeml-openrail-m 579 K 15.9 GB
284 Qwen3.8-4B-Distill-GGUF empero-ai · text-generation Open weights — — ✓ apache-2.0 579 K 3.6 GB
285 efficientnet_b0.ra_in1k timm · image-classification Open weights 10 M — ✓ apache-2.0 576 K 0.5 GB
286 bert-base-multilingual-uncased-sentiment nlptown · text-classification Open weights 170 M 512 ✓ mit 571 K 1.3 GB
287 gte-large thenlper · sentence-similarity Open weights 340 M 512 ✓ mit 570 K 1.3 GB
288 plamo-embedding-1b pfnet · sentence-similarity Open weights 1.1 B 4 K ✓ apache-2.0 567 K 3.0 GB
289 nemotron-3.5-asr-streaming-0.6b nvidia · ASR Open weights 640 M — other 560 K 1.4 GB
290 sanoTTS ampixa · text-to-speech Open weights — — gpl-3.0 559 K 0.5 GB
291 Spark-X2.5-4B-Heretic-jp-gguf soyaakinohara · text-generation Open weights 4.0 B — ✓ apache-2.0 556 K 4.0 GB
292 Qwen2.5-1.5B Qwen · text-generation Open weights 1.5 B 131 K ✓ apache-2.0 541 K 4.1 GB
293 Qwen3.8-9B-Distill-GGUF empero-ai · text-generation Open weights — — ✓ apache-2.0 540 K 6.9 GB
294 parakeet-tdt-0.6b-v3 nvidia · ASR Open weights 630 M — ✓ cc-by-4.0 540 K 1.4 GB
295 Llama-3.2-3B-Instruct unsloth · text-generation Open weights 3.2 B 131 K ⚠ llama3.2 536 K 8.0 GB
296 whisper-tiny Xenova · ASR Open weights 40 M — ✓ apache-2.0 534 K 0.6 GB
297 Qwen3.8-27B-OBLITERATED OBLITERATUS · text-generation Open weights 27.8 B — ✓ apache-2.0 533 K 5.7 GB
298 Qwen3-4B-GGUF unsloth · text-generation Open weights — 41 K ✓ apache-2.0 532 K 2.3 GB
299 snowflake-arctic-embed-xs Snowflake · sentence-similarity Open weights 20 M 512 unknown 531 K 0.6 GB
300 embeddinggemma-2-ONNX onnx-community · feature-extraction Open weights 744 M — ✓ apache-2.0 531 K 2.2 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.