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
301 nomic-embed-text-v2-moe nomic-ai · sentence-similarity Open weights 480 M — ✓ apache-2.0 736 K 2.7 GB
302 Qwen3-TTS-12Hz-0.6B-CustomVoice Qwen · text-to-speech Open weights 910 M — ✓ apache-2.0 734 K 3.4 GB
303 NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 nvidia · text-generation Open weights 18.2 B 262 K other 733 K 24.5 GB
304 pythia-70m-deduped EleutherAI · text-generation Open weights 100 M 2 K ✓ apache-2.0 729 K 0.7 GB
305 bert-large-cased-finetuned-conll03-english dbmdz · token-classification Open weights 330 M 512 unknown 719 K 2.0 GB
306 Qwen3-4B-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 719 K 3.2 GB
307 Z-Image-Turbo Tongyi-MAI · text-to-image Open weights 6.2 B — ✓ apache-2.0 715 K 37.5 GB
308 VibeVoice-ASR microsoft · ASR Open weights 8.7 B — ✓ mit 715 K 20.9 GB
309 Underdog-Saluki-27B-1.0 ConwayResearch · text-generation Open weights 27.0 B — ✗ cc-by-nc-4.0 710 K 5.2 GB
310 resnet50.ram_in1k timm · image-classification Open weights 30 M — ✓ apache-2.0 709 K 0.6 GB
311 vit-base-nsfw-detector AdamCodd · image-classification Open weights 90 M — ✓ apache-2.0 707 K 0.9 GB
312 Flux-2-Klein-9B Comfy-Org · text-to-image Open weights 9.0 B — other 707 K 37.3 GB
313 resnet34.a1_in1k timm · image-classification Open weights 20 M — ✓ apache-2.0 707 K 0.6 GB
314 gemma-4-31B-it-qat-NVFP4-Blackwell melcheikh · text-generation Open weights 31.0 B — ✓ apache-2.0 699 K 27.6 GB
315 FRIDA ai-forever · feature-extraction Open weights 823 M — ✓ mit 698 K 4.2 GB
316 whisper-large-v3-gguf handy-computer · ASR Open weights 1.5 B — ✓ apache-2.0 692 K 1.8 GB
317 Qwen3-VL-Embedding-8B Qwen · sentence-similarity Open weights 8.1 B — ✓ apache-2.0 690 K 19.6 GB
318 JEV-9B autotrust · text-classification Open weights 9.0 B 262 K ✓ apache-2.0 690 K 22.1 GB
319 Qwen2.5-14B-Instruct Qwen · text-generation Open weights 14.8 B 33 K ✓ apache-2.0 679 K 35.2 GB
320 Qwen2.5-32B-Instruct-GGUF bartowski · text-generation Open weights 32.0 B 33 K ✓ apache-2.0 676 K 15.2 GB
321 wav2vec2-xls-r-300m-bengali arijitx · ASR Open weights 300 M — ✓ apache-2.0 676 K 1.2 GB
322 nsfw-image-detection-384 Marqo · image-classification Open weights 5.6 M — ✓ apache-2.0 674 K 0.5 GB
323 whisper-large-v3-turbo-gguf handy-computer · ASR Open weights 810 M — ✓ mit 671 K 1.2 GB
324 Diplodocus-preview-GGUF OsaurusAI · text-generation Open weights — — ✓ apache-2.0 663 K 0.5 GB
325 whisper-medium-gguf handy-computer · ASR Open weights 760 M — ✓ apache-2.0 662 K 1.2 GB
326 noobai-XL-1.1 Laxhar · text-to-image Open weights 2.6 B — other 662 K 16.3 GB
327 multi-qa-MiniLM-L6-cos-v1 sentence-transformers · sentence-similarity Open weights 20 M 512 unknown 661 K 0.6 GB
328 convnext_tiny.in12k_ft_in1k timm · image-classification Open weights 30 M — ✓ apache-2.0 651 K 0.6 GB
329 whisper-tiny openai · ASR Open weights 40 M — ✓ apache-2.0 650 K 0.7 GB
330 wikineural-multilingual-ner Babelscape · token-classification Open weights 180 M 512 ✗ cc-by-nc-sa-4.0 649 K 1.3 GB
331 Qwen3-ASR-0.6B Qwen · ASR Open weights 940 M — ✓ apache-2.0 645 K 2.7 GB
332 LFM2.5-24B-A2B-Uncensored-GGUF AtomicChat · text-generation Open weights 24.0 B 131 K other 639 K 4.1 GB
333 MiniCPM5-2B-DSpark openbmb · text-generation Open weights 324 M 131 K ✓ apache-2.0 631 K 1.3 GB
334 Qwen3-1.7B-Base Qwen · text-generation Open weights 1.7 B 33 K ✓ apache-2.0 629 K 4.5 GB
335 sdxl-turbo stabilityai · text-to-image Open weights 2.6 B — other 626 K 46.7 GB
336 gpt-oss-20b-GGUF unsloth · text-generation Open weights — 131 K ✓ apache-2.0 624 K 13.1 GB
337 MiniCPM-SALA-AWQ-8bit cyankiwi · text-generation Open weights 3.1 B 524 K ✓ apache-2.0 621 K 12.7 GB
338 embeddinggemma-300m-ONNX onnx-community · sentence-similarity Open weights 300 M 2 K ⚠ gemma 617 K 1.2 GB
339 Qwen3-0.6B-Base Qwen · text-generation Open weights 600 M 33 K ✓ apache-2.0 612 K 1.9 GB
340 all-roberta-large-v1 sentence-transformers · sentence-similarity Open weights 360 M 512 ✓ apache-2.0 612 K 2.1 GB
341 Qwen3-TTS-12Hz-1.7B-VoiceDesign Qwen · text-to-speech Open weights 1.9 B — ✓ apache-2.0 608 K 5.8 GB
342 repvgg_a0.rvgg_in1k timm · image-classification Open weights 10 M — ✓ mit 608 K 0.5 GB
343 deepseek-v4-gguf antirez · text-generation Open weights — — ✓ mit 606 K 4.7 GB
344 Spark-X2.6-4B-GGUF XHToken · text-generation Open weights 4.0 B — ✓ apache-2.0 606 K 5.0 GB
345 DeepSeek-R1-Distill-Qwen-1.5B deepseek-ai · text-generation Open weights 1.8 B 131 K ✓ mit 600 K 4.7 GB
346 wav2vec2-large-xlsr-mvc-swahili eddiegulay · ASR Open weights 320 M — ✓ apache-2.0 600 K 1.9 GB
347 bloomz-560m bigscience · text-generation Open weights 560 M — ⚠ bigscience-bloom-rail-1.0 599 K 1.8 GB
348 bge-small-en-v1.5 michaelfeil · feature-extraction Open weights 30 M 512 ✓ mit 599 K 0.7 GB
349 wav2vec2-large-xls-r-300m-welsh infinitejoy · ASR Open weights 300 M — ✓ apache-2.0 591 K 1.2 GB
350 Qwen3.8-27B-Defiance-Uncensored-MTP-GGUF ttindall · text-generation Open weights 27.0 B — ✓ apache-2.0 590 K 5.5 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.