AImodelsComparison.com 1,086 open · 200 API
Menu
Models Best of Trending Can I run it? Methodology About
1,086 models · 1,086 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 1,286 Open weights (self-host) 1,086 API-only 200
Task
All text-generation 533 text-to-image 155 image-text-to-text 110 ASR 87 sentence-similarity 65 translation 55 text-classification 51 feature-extraction 48 image-classification 39 token-classification 21 text-to-speech 17 audio-classification 12 image-segmentation 10 object-detection 9 summarization 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
$
1,222 models
#ModelParamsContextCommercial use30dMin VRAM
601 Phi-3.5-mini-instruct microsoft · text-generation Open weights 3.8 B 131 K ✓ mit 376 K from 9.5 GB
602 snowflake-arctic-embed-m Snowflake · sentence-similarity Open weights 110 M 512 ✓ apache-2.0 376 K from 1.0 GB
603 plamo-embedding-1b pfnet · sentence-similarity Open weights 1.1 B 4 K ✓ apache-2.0 376 K from 3.0 GB
604 RVN-Qwen3.8-Flash-Next-Abliterated-Uncensored-IQ3_S-Strata jimmy31chen · text-generation Open weights — — ✓ apache-2.0 374 K from 98.3 GB
605 Spark-X2.5-4B-GGUF XHToken · text-generation Open weights 4.0 B — ✓ apache-2.0 373 K from 4.0 GB
606 gemma-2-9b-it-AWQ-INT4 hugging-quants · text-generation Open weights 9.2 B 8 K ⚠ gemma 371 K from 8.7 GB
607 cryptobert ElKulako · text-classification Open weights 120 M 512 ✓ mit 370 K from 1.1 GB
608 RMBG-2.0 briaai · image-segmentation · gated Open weights 221 M — other 369 K from 1.5 GB
609 Qwen3.8-27B-DFlash2 incoai · text-generation Open weights 1.9 B 262 K ✓ apache-2.0 369 K from 5.0 GB
610 GLM-5.3-GGUF unsloth · text-generation Open weights — — other 368 K from 52.0 GB
611 mistral-7b-v0.3-bnb-4bit unsloth · text-generation Open weights 7.5 B 33 K ✓ apache-2.0 367 K from 6.2 GB
612 snowflake-arctic-embed-xs Snowflake · sentence-similarity Open weights 20 M 512 unknown 365 K from 0.6 GB
613 phi-4 microsoft · text-generation Open weights Also via API 14.7 B 16 K ✓ mit 365 K from 34.9 GB
614 mask2former-swin-large-cityscapes-semantic facebook · image-segmentation Open weights 220 M — other 363 K from 1.5 GB
615 Qwen2.5-Coder-7B Qwen · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 363 K from 18.4 GB
616 DeepSeek-V4-Pro deepseek-ai · text-generation Open weights Also via API 1,598.8 B 1.0 M ✓ mit 361 K from 1,191.5 GB
617 deid_roberta_i2b2 obi · token-classification Open weights 350 M 512 ✓ mit 359 K from 2.1 GB
618 Meta-Llama-3-8B-Instruct meta-llama · text-generation · gated Open weights 8.0 B — ⚠ llama3 355 K from 19.4 GB
619 Juggernaut-XL-v9 RunDiffusion · text-to-image Open weights — — ⚠ creativeml-openrail-m 355 K from 15.9 GB
620 DeepSeek-R1-0528-Qwen3-8B deepseek-ai · text-generation Open weights 8.2 B 131 K ✓ mit 354 K from 19.7 GB
621 MuQ-large-msd-iter OpenMuQ · audio-classification Open weights 330 M — ✗ cc-by-nc-4.0 354 K from 2.0 GB
622 AI-image-detector umm-maybe · image-classification Open weights — — ✓ cc-by-4.0 353 K —
623 Qwen2.5-1.5B-Instruct-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 351 K from 1.3 GB
624 DeepSeek-R1-Distill-Qwen-32B deepseek-ai · text-generation Open weights 32.8 B 131 K ✓ mit 350 K from 77.5 GB
625 mms-lid-1024 facebook · audio-classification Open weights 967 M — ✗ cc-by-nc-4.0 347 K from 4.9 GB
626 koelectra-polite-v1 circulus · text-classification Open weights — 512 unknown 347 K —
627 inclusively-classification E-MIMIC · text-classification Open weights 110 M 512 ✗ cc-by-nc-sa-4.0 346 K from 1.0 GB
628 Phi-4-mini-instruct microsoft · text-generation Open weights 3.8 B 131 K ✓ mit 345 K from 9.5 GB
629 Qwen3.8-27B-DFlash2-GGUF z-lab · text-generation Open weights — — ✓ apache-2.0 343 K from 1.8 GB
630 Kimi-K2-Instruct moonshotai · text-generation Open weights Also via API 1,026.5 B 131 K other 343 K from 1,286.6 GB
631 Ornith-1.0-9B-GGUF unsloth · text-generation Open weights — — ✓ mit 343 K from 5.3 GB
632 Realistic_Vision_V5.1_noVAE SG161222 · text-to-image Open weights 860 M — ⚠ creativeml-openrail-m 343 K from 19.4 GB
633 bloom-560m bigscience · text-generation Open weights 560 M — ⚠ bigscience-bloom-rail-1.0 342 K from 1.8 GB
634 vit_small_patch16_224.augreg_in21k_ft_in1k timm · image-classification Open weights 20 M — ✓ apache-2.0 342 K from 0.6 GB
635 Ternary-Bonsai-8B-gguf prism-ml · text-generation Open weights — — ✓ apache-2.0 342 K from 2.9 GB
636 Qwen3-Coder-480B-A35B-Instruct-FP8 Qwen · text-generation Open weights 480.2 B 262 K ✓ apache-2.0 342 K from 602.9 GB
637 Phi-3-mini-4k-instruct microsoft · text-generation Open weights 3.8 B 4 K ✓ mit 341 K from 9.5 GB
638 granite-3.3-2b-instruct ibm-granite · text-generation Open weights 2.5 B 131 K ✓ apache-2.0 339 K from 6.5 GB
639 Huihui-DeepSeek-V4-Flash-0731-abliterated-GGUF huihui-ai · text-generation Open weights — — ✓ mit 339 K from 12.5 GB
640 LFM2.5-230M-GGUF LiquidAI · text-generation Open weights 230 M — other 338 K from 0.7 GB
641 Ornith-1.5-397B-FP8 ornith-ai · text-generation Open weights 403.4 B — ✓ mit 337 K from 521.2 GB
642 deberta-large-mnli microsoft · text-classification Open weights — 512 ✓ mit 336 K —
643 CodeLlama-7b-hf codellama · text-generation Open weights 6.7 B 16 K ⚠ llama2 335 K from 16.3 GB
644 LFM2.5-1.2B-Instruct-GGUF LiquidAI · text-generation Open weights 1.2 B 128 K other 334 K from 1.4 GB
645 MiniCPM5-1B openbmb · text-generation Open weights 1.1 B 131 K ✓ apache-2.0 333 K from 3.0 GB
646 Ornith-1.5-35B-A3B-MLX ornith-ai · text-generation Open weights 34.7 B — unknown 331 K from 82.0 GB
647 nsfw_image_detector Freepik · image-classification Open weights 90 M — ✓ mit 331 K from 0.7 GB
648 bert-small-pii-detection gravitee-io · token-classification Open weights 30 M 512 ✓ apache-2.0 329 K from 0.6 GB
649 Qwen3.6-27B-AWQ-4bit Alennnndy · text-generation Open weights 27.7 B — ✓ apache-2.0 329 K from 25.2 GB
650 table-transformer-detection microsoft · object-detection Open weights 30 M 1 K ✓ mit 327 K from 0.6 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.