AImodelsComparison.com 1,226 open · 200 API
Menu
Models Best of Trending Can I run it? Methodology About
1,226 models · 1,226 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 1,426 Open weights (self-host) 1,226 API-only 200
Task
All text-generation 534 text-to-image 155 image-text-to-text 112 ASR 86 sentence-similarity 64 translation 56 text-classification 51 feature-extraction 48 image-classification 39 token-classification 21 text-to-speech 19 audio-classification 12 image-segmentation 11 summarization 8 object-detection 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
$
112 models
#ModelParamsContextCommercial use30dMin VRAM
51 Dirk-Qwen3.8-27B-GGUF peculiar-ragdoll · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 1.3 M from 14.2 GB
52 Qwen3.6-27B-FP8 Qwen · image-text-to-text Open weights 27.8 B — ✓ apache-2.0 1.3 M from 38.6 GB
53 Qwen3.5-35B-A3B-FP8 Qwen · image-text-to-text Open weights 36.0 B — ✓ apache-2.0 1.2 M from 47.1 GB
54 Qwen3.6-35B-A3B-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 1.2 M from 11.6 GB
55 Qwen3.5-4B-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 1.2 M from 2.8 GB
56 Qwen3.8-27B-GSQ-RCO-GGUF ISTA-DASLab · image-text-to-text Open weights — — ✓ apache-2.0 1.2 M from 1.5 GB
57 gemma-4-26B-A4B-it-FP8-dynamic RedHatAI · image-text-to-text Open weights 26.5 B — ✓ apache-2.0 1.1 M from 36.0 GB
58 Qwen2-VL-2B-Instruct Qwen · image-text-to-text Open weights 2.2 B 33 K ✓ apache-2.0 1.1 M from 5.7 GB
59 gemma-4-31B-it-NVFP4 RedHatAI · image-text-to-text Open weights 32.7 B — ✓ apache-2.0 1.1 M from 31.0 GB
60 Qwen3.6-35B-A3B-MTP-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 1.1 M from 13.0 GB
61 Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V10-GGUF LuffyTheFox · image-text-to-text Open weights — — ✓ apache-2.0 1.1 M from 29.9 GB
62 Muse-Glimmer-30B-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 1.1 M from 12.3 GB
63 Qwen3.8-Flash-Next-GGUF unsloth · image-text-to-text Open weights 180.0 B — other 1.0 M from 30.6 GB
64 Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V11-GGUF LuffyTheFox · image-text-to-text Open weights — — ✓ apache-2.0 1.0 M from 29.9 GB
65 Qwen3.5-122B-A10B Qwen · image-text-to-text Open weights Also via API 125.1 B — ✓ apache-2.0 1.0 M from 294.5 GB
66 Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V9-GGUF LuffyTheFox · image-text-to-text Open weights — — ✓ apache-2.0 998 K from 29.8 GB
67 gemma-3-4b-it google · image-text-to-text · gated Open weights Also via API 4.3 B — ⚠ gemma 995 K from 10.6 GB
68 Qwen3.8-27B-NVFP4 RadixArk · image-text-to-text Open weights 18.2 B — ✓ apache-2.0 981 K from 27.3 GB
69 Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V12-GGUF LuffyTheFox · image-text-to-text Open weights — — ✓ apache-2.0 965 K from 29.9 GB
70 Qwen3.5-35B-A3B-GGUF unsloth · image-text-to-text Open weights 35.0 B — ✓ apache-2.0 964 K from 22.5 GB
71 gemma-4-26B-A4B-it-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 963 K from 11.4 GB
72 Qwen3-VL-8B-Instruct-GGUF Qwen · image-text-to-text Open weights 8.0 B — ✓ apache-2.0 945 K from 7.2 GB
73 Unlimited-OCR-AWQ sahilchachra · image-text-to-text Open weights 3.4 B 33 K ✓ mit 942 K from 4.1 GB
74 Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF ISTA-DASLab · image-text-to-text Open weights 180.0 B — ✓ apache-2.0 938 K from 28.5 GB
75 gemma-4-31B-it-FP8-block RedHatAI · image-text-to-text Open weights 31.3 B — ✓ apache-2.0 936 K from 41.8 GB
76 Qwen3.6-35B-A3B-NVFP4 RedHatAI · image-text-to-text Open weights 34.7 B — ✓ apache-2.0 929 K from 33.2 GB
77 Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-Final-GGUF LuffyTheFox · image-text-to-text Open weights — — ✓ apache-2.0 923 K from 26.0 GB
78 LocateAnything-3B nvidia · image-text-to-text Open weights 3.8 B — other 923 K from 9.5 GB
79 Kimi-K3 moonshotai · image-text-to-text Open weights Also via API 2,779.9 B — other 922 K from 2,134.5 GB
80 Qwythos-9B-Claude-Mythos-5-1M-GGUF empero-ai · image-text-to-text Open weights — — ✓ apache-2.0 922 K from 7.0 GB
81 Gemma-4-E4B-Uncensored-HauhauCS-Aggressive HauhauCS · image-text-to-text Open weights — — ⚠ gemma 920 K from 5.4 GB
82 llava-1.5-7b-hf llava-hf · image-text-to-text Open weights 7.1 B — ⚠ llama2 920 K from 17.1 GB
83 MiMo-V2.6-Distill-Qwen-9B-GGUF bartowski · image-text-to-text Open weights 9.0 B — unknown 920 K from 5.7 GB
84 Qwen3-VL-235B-A22B-Instruct Qwen · image-text-to-text Open weights Also via API 235.7 B — ✓ apache-2.0 916 K from 554.3 GB
85 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive HauhauCS · image-text-to-text Open weights — — ✓ apache-2.0 907 K from 13.3 GB
86 Qwen3.8-Flash-Next-Uncensored-GGUF orcarouter · image-text-to-text · gated Open weights 180.0 B — ✓ apache-2.0 899 K from 32.0 GB
87 Qwen3.8-27B-AWQ-INT4 cyankiwi · image-text-to-text Open weights 27.8 B — ✓ apache-2.0 898 K from 27.8 GB
88 Inkling-Small thinkingmachines · image-text-to-text Open weights Also via API 266.0 B — ✓ apache-2.0 884 K from 625.5 GB
89 Qwen3.8-27B-4bit mlx-community · image-text-to-text Open weights 27.4 B — ✓ apache-2.0 880 K from 22.3 GB
90 Qwen3.6-35B-A3B-NVFP4-Fast unsloth · image-text-to-text Open weights 35.0 B — ✓ apache-2.0 880 K from 31.8 GB
91 HunyuanOCR tencent · image-text-to-text Open weights 1.1 B — other 852 K from 5.7 GB
92 Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced HauhauCS · image-text-to-text Open weights 12.0 B — ⚠ gemma 832 K from 2.6 GB
93 gemma-4-26B-A4B-it-AWQ-4bit cyankiwi · image-text-to-text Open weights 25.8 B — ✓ apache-2.0 830 K from 23.3 GB
94 Qwen3.5-397B-A17B Qwen · image-text-to-text Open weights Also via API 403.4 B — ✓ apache-2.0 667 K from 948.5 GB
95 Muse-Glimmer-30B meta-models · image-text-to-text Open weights Also via API 29.8 B — ✓ apache-2.0 205 K from 70.5 GB
96 MiniMax-M3 MiniMaxAI · image-text-to-text Open weights Also via API 427.0 B — other 203 K from 1,004.2 GB
97 Llama-4-Scout-17B-16E-Instruct meta-llama · image-text-to-text · gated Open weights Also via API 108.6 B — other 145 K from 255.8 GB
98 Qwen2.5-VL-72B-Instruct Qwen · image-text-to-text Open weights Also via API 73.4 B 128 K other 89 K from 173.0 GB
99 Kimi-K2.7-Code moonshotai · image-text-to-text Open weights Also via API 1,026.9 B — other 89 K from 809.2 GB
100 moondream3-preview moondream · image-text-to-text Open weights Also via API 9.3 B — other 69 K from 42.7 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.