LLM EXPLORER 57,252 MODELS INDEXED

Gelato 30B A3B by mlfoundations

By mlfoundations · 30 downloads
HF Repo ↗ Copy URL

Gelato 30B A3B is an open-source language model by mlfoundations. Features: 30b LLM, VRAM: 62.1GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.21.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-30b-a...   Conversational Dataset:mlfoundations/click-10...   Deploy:azure   En   Endpoints compatible   Image-text-to-text   Instruct   Qwen3 vl moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlfoundations/Gelato-30B-A3B 

Gelato 30B A3B Parameters and Internals

LLM NameGelato 30B A3B
Repository 🤗https://huggingface.co/mlfoundations/Gelato-30B-A3B 
Base Model(s)  Qwen3 VL 30B A3B Instruct   Qwen/Qwen3-VL-30B-A3B-Instruct
Model Size30b
Required VRAM62.1 GB
Updated2026-08-08
Maintainermlfoundations
Model Typeqwen3_vl_moe
Instruction-BasedYes
Model Files  4.7 GB: 1-of-14   5.0 GB: 2-of-14   4.6 GB: 3-of-14   4.6 GB: 4-of-14   5.0 GB: 5-of-14   4.7 GB: 6-of-14   4.8 GB: 7-of-14   4.9 GB: 8-of-14   4.4 GB: 9-of-14   4.6 GB: 10-of-14   5.0 GB: 11-of-14   4.6 GB: 12-of-14   4.8 GB: 13-of-14   0.4 GB: 14-of-14
Supported Languagesen
Model ArchitectureQwen3VLMoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Gelato 30B A3B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 30B A3B Instruct0K / 62.3 GB488106591
Qwen3 VL 30B A3B Instruct FP80K / 32.2 GB734631115
Bu 30B A3b Preview0K / 62.3 GB1035263
Qwen3 VL 30B A3B Instruct0K / 62.3 GB5153
Qwen3 VL 30B A3B Instruct Bf160K / 62.3 GB874
Qwen3 VL 30B A3B Instruct 4bit0K / 18.3 GB9258
Qwen3 VL 30B A3B Instruct 8bit0K / 33.5 GB2313
Qwen3 VL 30B A3B Instruct 6bit0K / 25.8 GB722
Qwen3 VL 30B A3B Instruct AWQ0K / 17.9 GB118470445
Note: green Score (e.g. "73.2") means that the model is better than mlfoundations/Gelato-30B-A3B.