AImodelsComparison.com 1,213 open · 210 API
Menu
Models Best of Trending Can I run it? Methodology MCP server About
1,423 models · 1,213 open weights · 210 API-only · refreshed nightly

All models

Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

Type
All 1,423 Open weights (self-host) 1,213 API-only 210
Task
All text-generation 735 text-to-image 165 image-text-to-text 110 ASR 82 sentence-similarity 63 text-classification 50 translation 50 feature-extraction 46 image-classification 41 text-to-speech 23 token-classification 22 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
$
1,423 models
#ModelParamsContextCommercial use30dMin VRAM
601 wavlm-base-plus microsoft · feature-extraction Open weights — — unknown 396 K —
602 mistral-7b-v0.3-bnb-4bit unsloth · text-generation Open weights 7.5 B 33 K ✓ apache-2.0 392 K from 6.2 GB
603 swinv2-tiny-patch4-window16-256 microsoft · image-classification Open weights — — ✓ apache-2.0 390 K —
604 Qwen2.5-Coder-1.5B Qwen · text-generation Open weights 1.5 B 33 K ✓ apache-2.0 387 K from 4.1 GB
605 Ornith-1.0-397B deepreinforce-ai · text-generation Open weights 396.8 B — ✓ mit 387 K from 933.0 GB
606 SmolLM3-3B HuggingFaceTB · text-generation Open weights 3.1 B 66 K ✓ apache-2.0 386 K from 7.7 GB
607 Meta-Llama-3-8B-Instruct meta-llama · text-generation · gated Open weights 8.0 B — ⚠ llama3 386 K from 19.4 GB
608 opus-mt-mul-en Helsinki-NLP · translation Open weights — 512 ✓ apache-2.0 382 K —
609 emotion-english-distilroberta-base j-hartmann · text-classification Open weights — 512 unknown 381 K —
610 humanizer jialinyyzz · text-generation Open weights 12.0 B — ✓ apache-2.0 380 K from 6.6 GB
611 MegaDescriptor-T-224 BVRA · image-classification Open weights — — ✗ cc-by-nc-4.0 380 K —
612 Qwen-Image-2.1-Turbo-GGUF DogukanUrker · text-to-image Open weights — — other 379 K from 3.1 GB
613 Qwen3-Coder-Next-FP8 Qwen · text-generation Open weights 79.7 B 262 K ✓ apache-2.0 378 K from 100.9 GB
614 bloom-560m bigscience · text-generation Open weights 560 M — ⚠ bigscience-bloom-rail-1.0 378 K from 1.8 GB
615 Qwen2.5-Coder-7B Qwen · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 377 K from 18.4 GB
616 Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF huihui-ai · text-generation Open weights — — ✓ mit 377 K from 12.5 GB
617 Qwen2.5-Coder-7B-Instruct-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 376 K from 3.8 GB
618 audiobox-aesthetics facebook · audio-classification Open weights 100 M — ✓ cc-by-4.0 375 K from 1.0 GB
619 RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored-IQ3_S-Strata jimmy31chen · text-generation Open weights — — ✓ apache-2.0 373 K from 98.3 GB
620 DeepSeek-R1-0528-Qwen3-8B deepseek-ai · text-generation Open weights 8.2 B 131 K ✓ mit 371 K from 19.7 GB
621 deid_roberta_i2b2 obi · token-classification Open weights 350 M 512 ✓ mit 369 K from 2.1 GB
622 Phi-3.5-mini-instruct microsoft · text-generation Open weights 3.8 B 131 K ✓ mit 367 K from 9.5 GB
623 spark-s1-4b-v6-GGUF abhishek085 · text-classification Open weights 4.0 B — ✓ apache-2.0 367 K from 4.9 GB
624 DreamShaper Lykon · text-to-image Open weights — — other 366 K from 185.3 GB
625 Ornith-1.5-397B-FP8 ornith-ai · text-generation Open weights 403.4 B — ✓ mit 365 K from 521.2 GB
626 Qwen3-4B-Thinking-2507 Qwen · text-generation Open weights 4.0 B 262 K ✓ apache-2.0 364 K from 10.0 GB
627 fullstop-punctuation-multilang-large oliverguhr · token-classification Open weights 560 M 512 ✓ mit 363 K from 3.0 GB
628 Ornith-1.5-35B-A3B-MLX ornith-ai · text-generation Open weights 34.7 B — unknown 358 K from 82.0 GB
629 DeepSeek-R1-Distill-Qwen-32B deepseek-ai · text-generation Open weights 32.8 B 131 K ✓ mit 358 K from 77.5 GB
630 gpt-oss-20b-GGUF ggml-org · text-generation Open weights 20.0 B 131 K ✓ apache-2.0 356 K from 4.5 GB
631 roberta-base-openai-detector openai-community · text-classification Open weights 125 M 512 ✓ mit 353 K from 1.1 GB
632 AI-image-detector umm-maybe · image-classification Open weights — — ✓ cc-by-4.0 353 K —
633 GLM-5.3-GGUF unsloth · text-generation Open weights — — other 352 K from 52.0 GB
634 Llama-3.3-70B-Instruct meta-llama · text-generation · gated Open weights Also via API 70.6 B — ⚠ llama3.3 351 K from 166.3 GB
635 convnext_base.fb_in22k_ft_in1k timm · image-classification Open weights 90 M — ✓ apache-2.0 350 K from 0.9 GB
636 wide_resnet101_2.tv_in1k timm · image-classification Open weights 127 M — ✓ bsd-3-clause 350 K from 1.1 GB
637 Meta-Llama-3.1-8B-Instruct-GGUF bartowski · text-generation Open weights — — ⚠ llama3.1 344 K from 3.7 GB
638 deepseek-v4-flash-0731-spark 0xSero · text-generation Open weights 60.3 B 1.0 M ✓ mit 340 K from 127.0 GB
639 Hermes-3-Llama-3.1-8B NousResearch · text-generation Open weights 8.0 B 131 K ⚠ llama3 339 K from 19.4 GB
640 Spark-X2.5-4B-GGUF abenzerps · text-generation Open weights 4.0 B — ✓ apache-2.0 338 K from 3.7 GB
641 Qwen3-Coder-Next-8bit NexVeridian · text-generation Open weights 79.7 B 262 K ✓ apache-2.0 336 K from 105.6 GB
642 Z-Image-Lora nphSi · text-to-image Open weights 6.2 B — ✓ apache-2.0 336 K from 118.0 GB
643 mask2former-swin-large-ade-semantic facebook · image-segmentation Open weights 220 M — other 336 K from 1.5 GB
644 DeepSeek-V4-Pro deepseek-ai · text-generation Open weights Also via API 1,598.8 B 1.0 M ✓ mit 336 K from 1,191.5 GB
645 Pony_Diffusion_V6_XL LyliaEngine · text-to-image Open weights — — cdla-permissive-2.0 335 K from 8.5 GB
646 resnet-18 microsoft · image-classification Open weights 12 M — ✓ apache-2.0 333 K from 0.6 GB
647 Phi-4-mini-instruct microsoft · text-generation Open weights 3.8 B 131 K ✓ mit 332 K from 9.5 GB
648 Ornith-1.5-9B-OBLITERATED OBLITERATUS · text-generation Open weights 9.7 B — ✓ mit 332 K from 6.3 GB
649 MegaDescriptor-B-224 BVRA · image-classification Open weights — — ✗ cc-by-nc-4.0 331 K —
650 Z-Image-Turbo unsloth · text-to-image Open weights 6.2 B — ✓ apache-2.0 329 K from 37.5 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.