AImodelsComparison.com 1,222 open · 200 API
Menu
Models Best of Trending Can I run it? Methodology About
1,222 models · 1,222 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 1,422 Open weights (self-host) 1,222 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
701 bertweet-base-sentiment-analysis finiteautomata · text-classification Open weights — 128 unknown 267 K —
702 taardis-27b-full-ternary CodeMasterCody3D · text-generation Open weights 27.0 B — ✓ apache-2.0 267 K from 12.4 GB
703 gliner2.5-multi-v1 fastino · token-classification Open weights 287 M — ✓ apache-2.0 266 K from 1.8 GB
704 Step-3.5-Flash stepfun-ai · text-generation Open weights Also via API 199.4 B 262 K ✓ apache-2.0 265 K from 469.1 GB
705 Qwen3-30B-A3B-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 265 K from 20.9 GB
706 Ornith-1.0-397B-FP8 ornith-ai · text-generation Open weights 396.8 B — ✓ mit 265 K from 505.7 GB
707 Ornith-1.5-35B-A3B ornith-ai · text-generation Open weights 36.0 B — ✓ mit 264 K from 85.0 GB
708 ner-english-fast flair · token-classification Open weights — — unknown 259 K —
709 Qwen3.8-4B-Distill empero-ai · text-generation Open weights 4.7 B — ✓ apache-2.0 258 K from 11.5 GB
710 rubert-tiny-toxicity cointegrated · text-classification Open weights 10 M 512 ✓ mit 258 K from 0.6 GB
711 SmolLM2-1.7B-Instruct HuggingFaceTB · text-generation Open weights 1.7 B 8 K ✓ apache-2.0 257 K from 4.5 GB
712 resnet-50 microsoft · image-classification Open weights 30 M — ✓ apache-2.0 255 K from 0.6 GB
713 OpenMed-NER-PharmaDetect-SuperClinical-434M OpenMed · token-classification Open weights 430 M 512 ✓ apache-2.0 255 K from 1.5 GB
714 Qwen3-14B-GGUF Qwen · text-generation Open weights — — ✓ apache-2.0 253 K from 10.4 GB
715 FinancialBERT-Sentiment-Analysis ahmedrachid · text-classification Open weights — 512 unknown 253 K —
716 roberta-large-mnli FacebookAI · text-classification Open weights 360 M 512 ✓ mit 253 K from 2.1 GB
717 Qwen3-8B-64k-Context-2X-Josiefied-Uncensored DavidAU · text-generation Open weights 8.2 B 66 K unknown 253 K from 19.7 GB
718 opus-mt-en-ru Helsinki-NLP · translation Open weights — 512 ✓ apache-2.0 253 K —
719 droplychee-1.0-27b droplychee · text-generation Open weights 27.8 B — ✓ apache-2.0 252 K from 65.8 GB
720 Llama-3.3-70B-Instruct meta-llama · text-generation · gated Open weights Also via API 70.6 B — ⚠ llama3.3 252 K from 166.3 GB
721 Qwen2.5-1.5B-apeach jason9693 · text-classification Open weights 1.5 B 131 K unknown 251 K from 7.5 GB
722 gemma-2-2b-it google · text-generation · gated Open weights 2.6 B — ⚠ gemma 251 K from 6.6 GB
723 Qwen2-0.5B-Instruct Qwen · text-generation Open weights 490 M 33 K ✓ apache-2.0 250 K from 1.7 GB
724 Qwen3.8-27B-DSpark RadixArk · text-generation Open weights 1.9 B 262 K other 250 K from 4.9 GB
725 Qwen2.5-Coder-7B-Instruct-4bit mlx-community · text-generation Open weights 1.2 B 33 K ✓ apache-2.0 249 K from 5.4 GB
726 gpt-neox-20b EleutherAI · text-generation Open weights 20.7 B 2 K ✓ apache-2.0 249 K from 49.0 GB
727 vit_base_patch8_224.augreg2_in21k_ft_in1k timm · image-classification Open weights 90 M — ✓ apache-2.0 248 K from 0.9 GB
728 Hy3-GGUF vcruz305 · text-generation Open weights — — ✓ apache-2.0 248 K from 52.9 GB
729 fairface_age_image_detection dima806 · image-classification Open weights 90 M — ✓ apache-2.0 248 K from 2.4 GB
730 Kwaipilot_KAT-Coder-V2.5-Dev-GGUF bartowski · text-generation Open weights — — ✓ apache-2.0 248 K from 11.3 GB
731 nllb-200-3.3B facebook · translation Open weights 3.3 B 1 K ✗ cc-by-nc-4.0 248 K from 8.3 GB
732 EXAONE-3.5-7.8B-Instruct LGAI-EXAONE · text-generation Open weights 7.8 B 33 K other 248 K from 36.1 GB
733 llama-3-8b-Instruct-bnb-4bit unsloth · text-generation Open weights 8.2 B 8 K ⚠ llama3 247 K from 8.0 GB
734 Ornith-1.5-9B-MLX-4bit ornith-ai · text-generation Open weights 9.0 B — unknown 247 K from 7.4 GB
735 NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 nvidia · text-generation Open weights 31.6 B 262 K other 246 K from 41.2 GB
736 Phi-3-mini-128k-instruct microsoft · text-generation Open weights 3.8 B 131 K ✓ mit 246 K from 9.5 GB
737 xlm-roberta-large-ner-hrl Davlan · token-classification Open weights 560 M 512 ✓ afl-3.0 246 K from 3.0 GB
738 Mistral-Small-3.1-24B-Instruct-2503 mistralai · text-generation Open weights Also via API 24.0 B — ✓ apache-2.0 246 K from 109.8 GB
739 DeepSeek-V4-Flash-GGUF bartowski · text-generation Open weights — — ✓ mit 245 K from 44.1 GB
740 Qwen3.8-Flash-Next-NVFP4-GPTQ-Strata Maximilian228 · text-generation Open weights 180.0 B — other 245 K from 83.8 GB
741 plant-identity umutbozdag · image-classification Open weights 90 M — unknown 245 K from 0.9 GB
742 Pony_Diffusion_V6_XL LyliaEngine · text-to-image Open weights — — cdla-permissive-2.0 245 K from 8.5 GB
743 OTel-LLM-8B-A1B-IT farbodtavakkoli · text-generation Open weights — 128 K ✓ apache-2.0 245 K —
744 RMBG-1.4 briaai · image-segmentation Open weights 40 M — other 245 K from 0.7 GB
745 convnext_small.fb_in22k_ft_in1k_384 timm · image-classification Open weights 50 M — ✓ apache-2.0 245 K from 0.7 GB
746 Qwen_Qwen3-4B-GGUF bartowski · text-generation Open weights 4.0 B 41 K unknown 244 K from 2.8 GB
747 Z-Image-Lora nphSi · text-to-image Open weights 6.2 B — ✓ apache-2.0 244 K from 114.6 GB
748 mmarco-mMiniLMv2-L6-H384-v1 nreimers · text-classification Open weights — 512 unknown 244 K —
749 Qwen-Image-2.1 unsloth · text-to-image Open weights 7.1 B — other 243 K from 38.0 GB
750 Ling-3.0-tiny-GGUF bloomer010 · text-generation Open weights — 131 K ✓ mit 243 K from 2.4 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.