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
951 Qwen2.5-Math-7B-4bit LLMSafety · text-generation Open weights 7.8 B 4 K unknown 168 K from 7.8 GB
952 stable-diffusion-v1-1 CompVis · text-to-image Open weights — — ⚠ creativeml-openrail-m 168 K from 3.5 GB
953 gpt-oss-20b-MXFP4-Q8 mlx-community · text-generation Open weights 20.9 B 131 K ✓ apache-2.0 167 K from 16.9 GB
954 Llama-3.2-3B-Instruct-GGUF bartowski · text-generation Open weights — — ⚠ llama3.2 167 K from 2.3 GB
955 transformer-1.3B-100B fla-hub · text-generation Open weights 1.4 B 2 K ✓ mit 166 K from 3.7 GB
956 DeepSeek-R1-0528 deepseek-ai · text-generation Open weights Also via API 684.5 B 164 K ✓ mit 165 K from 860.6 GB
957 gpt2-medium openai-community · text-generation Open weights 380 M — ✓ mit 165 K from 2.2 GB
958 DeepSeek-R1-0528-Qwen3-8B-MLX-8bit lmstudio-community · text-generation Open weights 2.3 B 131 K ✓ mit 164 K from 10.4 GB
959 Parable-Granite-4.1-3B-Claude-Fable-5-GGUF AnkitAI · text-generation Open weights 3.0 B 131 K ✓ apache-2.0 164 K from 3.3 GB
960 GLM-5.2-FP8 zai-org · text-generation Open weights 753.3 B 1.0 M ✓ mit 164 K from 944.7 GB
961 Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8 QuantTrio · text-generation Open weights 30.5 B 262 K ✓ apache-2.0 163 K from 40.3 GB
962 Parable-Granite-4.1-8B-Claude-Fable-5-GGUF AnkitAI · text-generation Open weights 8.0 B 131 K ✓ apache-2.0 162 K from 7.3 GB
963 Olmo-3-1025-7B allenai · text-generation Open weights 7.3 B 66 K ✓ apache-2.0 160 K from 17.7 GB
964 GLM-4.7-Flash-MLX-6bit lmstudio-community · text-generation Open weights 29.9 B 203 K ✓ mit 159 K from 31.8 GB
965 gemma-2-27b-it-GGUF bartowski · text-generation Open weights 27.0 B — ⚠ gemma 158 K from 13.8 GB
966 Meta-Llama-3.1-8B-Instruct-AWQ-INT4 hugging-quants · text-generation Open weights 8.0 B 131 K ⚠ llama3.1 158 K from 8.0 GB
967 pythia-410m EleutherAI · text-generation Open weights 510 M 2 K ✓ apache-2.0 158 K from 1.6 GB
968 nova-furry-xl-il-v120-sdxl John6666 · text-to-image Open weights 2.6 B — other 157 K from 8.5 GB
969 Mistral-7B-v0.1-GGUF MaziyarPanahi · text-generation Open weights 7.0 B 33 K ✓ apache-2.0 157 K from 4.5 GB
970 LCM_Dreamshaper_v7 SimianLuo · text-to-image Open weights 860 M — ✓ mit 155 K from 10.4 GB
971 RealVisXL_V4.0 SG161222 · text-to-image Open weights 2.6 B — ⚠ openrail++ 154 K from 31.4 GB
972 Qwen2.5-14B-Instruct-GGUF bartowski · text-generation Open weights 14.0 B 33 K ✓ apache-2.0 154 K from 8.5 GB
973 Ornith-1.5-35B-A3B-MLX-6bit ornith-ai · text-generation Open weights 34.7 B — unknown 154 K from 36.7 GB
974 Qwen3-Next-80B-A3B-Instruct Qwen · text-generation Open weights Also via API 81.3 B 262 K ✓ apache-2.0 154 K from 191.6 GB
975 Qwen3-4B-Instruct-2507-unsloth-bnb-4bit unsloth · text-generation Open weights 4.0 B 262 K ✓ apache-2.0 153 K from 5.0 GB
976 Z-Image-Turbo unsloth · text-to-image Open weights 6.2 B — ✓ apache-2.0 152 K from 37.5 GB
977 Inkling-Small-DSpark-Preview RadixArk · text-generation Open weights 1.4 B 1.0 M unknown 151 K from 2.7 GB
978 DeepSeek-V4-Pro-0813 deepseek-ai · text-generation Open weights Also via API 1,650.5 B 1.0 M ✓ mit 151 K from 1,230.1 GB
979 Qwen3-14B-unsloth-bnb-4bit unsloth · text-generation Open weights 15.2 B 41 K ✓ apache-2.0 151 K from 15.0 GB
980 controlnet-union-sdxl-1.0 xinsir · text-to-image Open weights 1.3 B — ✓ apache-2.0 150 K from 6.2 GB
981 opus-mt-es-en Helsinki-NLP · translation Open weights — 512 ✓ apache-2.0 150 K —
982 Qwen3.6-27B-GGUF batiai · text-generation Open weights 27.0 B — ✓ apache-2.0 150 K from 5.6 GB
983 LFM2.5-230M-Base LiquidAI · text-generation Open weights 230 M 128 K other 149 K from 1.0 GB
984 DeepSeek-V4-Flash-DSpark deepseek-ai · text-generation Open weights 165.3 B 1.0 M ✓ mit 149 K from 208.9 GB
985 Qwen2.5-7B-Instruct unsloth · text-generation Open weights 7.6 B 33 K ✓ apache-2.0 149 K from 18.4 GB
986 Llama-3.2-1B-Instruct-GGUF bartowski · text-generation Open weights — — ⚠ llama3.2 147 K from 1.2 GB
987 DeepSeek-V2-Lite deepseek-ai · text-generation Open weights 15.7 B 164 K other 147 K from 37.4 GB
988 SDXL-Lightning ByteDance · text-to-image Open weights — — ⚠ openrail++ 146 K from 54.9 GB
989 Qwen3.8-27B-Uncensored-GGUF azukivc · text-generation Open weights 27.0 B — ✓ apache-2.0 145 K from 5.6 GB
990 Qwen2.5-Coder-0.5B-Instruct Qwen · text-generation Open weights 494 M 33 K ✓ apache-2.0 145 K from 1.7 GB
991 MiMo-V2.5 XiaomiMiMo · text-generation Open weights Also via API 310.8 B 1.0 M ✓ mit 144 K from 394.4 GB
992 Qwen3-0.6B-GGUF unsloth · text-generation Open weights 600 M 41 K ✓ apache-2.0 143 K from 0.9 GB
993 Kimi-Linear-48B-A3B-Instruct moonshotai · text-generation Open weights 49.1 B — ✓ mit 143 K from 115.9 GB
994 Meta-Llama-3.1-8B-Instruct NousResearch · text-generation Open weights 8.0 B 131 K ⚠ llama3.1 143 K from 19.4 GB
995 SmolLM-135M-Instruct-FP32 modularai · text-generation Open weights 135 M 2 K unknown 143 K from 1.1 GB
996 Llama-4-Scout-17B-16E-Instruct meta-llama · image-text-to-text · gated Open weights Also via API 108.6 B — other 143 K from 255.8 GB
997 Qwen3-Coder-Next-GGUF unsloth · text-generation Open weights — — ✓ apache-2.0 141 K from 47.4 GB
998 gpt-oss-120b-Eagle3-short-context nvidia · text-generation Open weights 787 M 131 K other 141 K from 2.8 GB
999 Mellum2-12B-A2.5B-Instruct-GGUF-Q8_0 JetBrains · text-generation Open weights — — ✓ apache-2.0 141 K from 14.7 GB
1000 pythia-160m-deduped EleutherAI · text-generation Open weights 210 M 2 K ✓ apache-2.0 140 K from 0.9 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.