LLM EXPLORER 60,062 MODELS INDEXED

EvoCUA 32B 20260105 by meituan

By meituan · 688 downloads
HF Repo ↗ Copy URL

EvoCUA 32B 20260105 is an open-source language model by meituan. Features: 32b LLM, VRAM: 67GB, License: apache-2.0, LLM Explorer Score: 0.24.

  Arxiv:2509.02544   Arxiv:2511.21631   Arxiv:2601.15876   Arxiv:2602.08235   Computer-use   En   Gui-agent   Multimodal   Osworld   Qwen3 vl   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/meituan/EvoCUA-32B-20260105 

EvoCUA 32B 20260105 Parameters and Internals

LLM NameEvoCUA 32B 20260105
Repository 🤗https://huggingface.co/meituan/EvoCUA-32B-20260105 
Model Size32b
Required VRAM67 GB
Updated2026-08-31
Maintainermeituan
Model Typeqwen3_vl
Model Files  4.9 GB: 1-of-14   4.9 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.9 GB: 8-of-14   4.9 GB: 9-of-14   4.9 GB: 10-of-14   4.9 GB: 11-of-14   4.9 GB: 12-of-14   4.9 GB: 13-of-14   3.3 GB: 14-of-14
Supported Languagesen zh
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to EvoCUA 32B 20260105

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 32B Instruct0K / 67 GB2881482223
Qwen3 VL 32B Instruct FP80K / 35.7 GB38061947
Cosmos Reason2 32B0K / 66.4 GB266214
Qwen3 VL 32B Thinking0K / 67 GB1566687
Qwen3 VL 32B Thinking FP80K / 35.7 GB1143127
... Vl 32B Minimax H3 Fp8 Comfyui0K / 26.5 GB111
...wen3 VL 32B Abliterated XCloud0K / 67 GB60
Qwen3 VL 32B Instruct0K / 67 GB3305
Qwen3 VL 32B Thinking FP80K / 35.7 GB272
Qwen3 VL 32B Instruct FP80K / 35.7 GB301
Note: green Score (e.g. "73.2") means that the model is better than meituan/EvoCUA-32B-20260105.