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
01 gemma-4-26B-A4B-it google · image-text-to-text Open weights Also via API 26.5 B — ✓ apache-2.0 9.1 M from 61.3 GB
02 gemma-4-31B-it google · image-text-to-text Open weights Also via API 32.7 B — ✓ apache-2.0 8.5 M from 74.2 GB
03 Qwen3.8-27B Qwen · image-text-to-text Open weights Also via API 27.8 B — ✓ apache-2.0 7.7 M from 65.8 GB
04 Qwen3.5-4B Qwen · image-text-to-text Open weights 4.7 B — ✓ apache-2.0 7.5 M from 11.5 GB
05 Qwen3.8-Flash-Next-GSQ-RCO-GGUF ISTA-DASLab · image-text-to-text Open weights 180.0 B — ✓ apache-2.0 6.5 M from 28.5 GB
06 Qwen3.5-9B Qwen · image-text-to-text Open weights Also via API 9.7 B — ✓ apache-2.0 6.4 M from 23.2 GB
07 GLM-5.3-Flash zai-org · image-text-to-text Open weights Also via API 321.3 B — ✓ mit 6.3 M from 409.9 GB
08 Qwen2.5-VL-7B-Instruct Qwen · image-text-to-text Open weights 8.3 B 128 K ✓ apache-2.0 4.9 M from 20.0 GB
09 Qwen3-VL-8B-Instruct Qwen · image-text-to-text Open weights Also via API 8.8 B — ✓ apache-2.0 4.8 M from 21.1 GB
10 Qwen3.8-27B-FP8 Qwen · image-text-to-text Open weights 27.8 B — ✓ apache-2.0 4.3 M from 38.6 GB
11 Qwen3.8-27B-MLX-4bit lmstudio-community · image-text-to-text Open weights 4.7 B — ✓ apache-2.0 3.7 M from 18.9 GB
12 Qwen3.6-35B-A3B Qwen · image-text-to-text Open weights Also via API 36.0 B — ✓ apache-2.0 3.7 M from 85.0 GB
13 Qwen3-VL-4B-Instruct Qwen · image-text-to-text Open weights 4.4 B — ✓ apache-2.0 3.6 M from 10.9 GB
14 Qwen3.8-27B-MLX-8bit lmstudio-community · image-text-to-text Open weights 8.0 B — ✓ apache-2.0 3.6 M from 34.2 GB
15 Qwen3.8-27B-MLX-6bit lmstudio-community · image-text-to-text Open weights 6.4 B — ✓ apache-2.0 3.6 M from 26.5 GB
16 Qwen3.8-27B-MLX-5bit lmstudio-community · image-text-to-text Open weights 5.5 B — ✓ apache-2.0 3.6 M from 22.7 GB
17 Qwen3.6-35B-A3B-FP8 Qwen · image-text-to-text Open weights 36.0 B — ✓ apache-2.0 3.5 M from 47.1 GB
18 Qwen3.5-0.8B Qwen · image-text-to-text Open weights 870 M — ✓ apache-2.0 3.3 M from 2.6 GB
19 Qwen3.5-2B Qwen · image-text-to-text Open weights 2.3 B — ✓ apache-2.0 2.9 M from 5.8 GB
20 Florence-2-base microsoft · image-text-to-text Open weights 230 M — ✓ mit 2.9 M from 1.0 GB
21 Qwen3.8-Flash-Next Qwen · image-text-to-text Open weights Also via API 180.0 B — other 2.8 M from 423.5 GB
22 Huihui-Qwen3.8-27B-abliterated-GGUF huihui-ai · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 2.4 M from 16.5 GB
23 Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF cdiamond · image-text-to-text Open weights — — ✓ apache-2.0 2.4 M from 19.3 GB
24 Qwen3.6-27B Qwen · image-text-to-text Open weights Also via API 27.8 B — ✓ apache-2.0 2.4 M from 65.8 GB
25 moondream2 vikhyatk · image-text-to-text Open weights 1.9 B — ✓ apache-2.0 2.3 M from 5.0 GB
26 Unlimited-OCR baidu · image-text-to-text Open weights 3.3 B 33 K ✓ mit 2.3 M from 15.7 GB
27 Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF HauhauCS · image-text-to-text Open weights — — ✓ apache-2.0 2.3 M from 1.5 GB
28 Qwen3.8-27B-GGUF ggml-org · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 2.2 M from 6.4 GB
29 JEV-27B-VL autotrust · image-text-to-text Open weights 27.8 B — ✓ apache-2.0 2.2 M from 66.3 GB
30 Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF SC117 · image-text-to-text Open weights 180.0 B — ✓ apache-2.0 2.1 M from 28.5 GB
31 DeepSeek-OCR deepseek-ai · image-text-to-text Open weights 3.3 B 8 K ✓ mit 2.0 M from 8.3 GB
32 Tiel-Coder-35B-A3B-GGUF-MTP peculiar-ragdoll · image-text-to-text Open weights 35.0 B — ✓ mit 2.0 M from 19.7 GB
33 Qwen3.8-27B-GGUF byteshape · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 2.0 M from 5.6 GB
34 GLM-OCR zai-org · image-text-to-text Open weights 1.3 B — ✓ mit 2.0 M from 3.6 GB
35 Qwen3-VL-2B-Instruct Qwen · image-text-to-text Open weights 2.1 B — ✓ apache-2.0 1.9 M from 5.5 GB
36 Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF DavidAU · image-text-to-text Open weights 9.0 B — ✓ apache-2.0 1.8 M from 7.3 GB
37 Qwen2.5-VL-7B-Instruct-AWQ Qwen · image-text-to-text Open weights 8.3 B 128 K ✓ apache-2.0 1.7 M from 9.4 GB
38 Qwen2.5-VL-3B-Instruct Qwen · image-text-to-text Open weights 3.8 B 128 K unknown 1.7 M from 9.3 GB
39 Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF DavidAU · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 1.7 M from 17.9 GB
40 Qwen3.5-27B Qwen · image-text-to-text Open weights Also via API 27.8 B — ✓ apache-2.0 1.7 M from 65.8 GB
41 gemma-4-12b-it-GGUF unsloth · image-text-to-text Open weights 12.0 B — ✓ apache-2.0 1.5 M from 7.9 GB
42 Qwen2-VL-7B-Instruct-AWQ Qwen · image-text-to-text Open weights 8.3 B 33 K ✓ apache-2.0 1.5 M from 9.4 GB
43 DeepSeek-V4.1-Flash deepseek-ai · image-text-to-text Open weights Also via API 763.2 B — ✓ mit 1.5 M from 676.3 GB
44 SmolVLM2-500M-Video-Instruct HuggingFaceTB · image-text-to-text Open weights 510 M — ✓ apache-2.0 1.4 M from 2.8 GB
45 Inkling thinkingmachines · image-text-to-text Open weights Also via API 952.4 B — ✓ apache-2.0 1.4 M from 2,238.6 GB
46 surya-ocr-2 datalab-to · image-text-to-text Open weights 690 M — ⚠ openrail 1.4 M from 2.1 GB
47 Qwen3.5-35B-A3B Qwen · image-text-to-text Open weights Also via API 36.0 B — ✓ apache-2.0 1.4 M from 85.0 GB
48 chandra-ocr-2 datalab-to · image-text-to-text Open weights 5.3 B — ⚠ openrail 1.4 M from 12.9 GB
49 Qwen3-VL-8B-Instruct-FP8 Qwen · image-text-to-text Open weights 8.8 B — ✓ apache-2.0 1.4 M from 13.5 GB
50 Qwen3.5-9B-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 1.3 M from 5.2 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.