LLM EXPLORER 60,702 MODELS INDEXED

Qwen3.5 122B A10B Mxfp4 by mlx-community

By mlx-community · 114 downloads
HF Repo ↗ Copy URL

Qwen3.5 122B A10B Mxfp4 is an open-source language model by mlx-community. Features: 122b LLM, VRAM: 65.4GB, License: apache-2.0, LLM Explorer Score: 0.24.

  4-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-122b-a...   Conversational   Image-text-to-text   Mlx   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-mxfp4 

Qwen3.5 122B A10B Mxfp4 Parameters and Internals

LLM NameQwen3.5 122B A10B Mxfp4
Repository 🤗https://huggingface.co/mlx-community/Qwen3.5-122B-A10B-mxfp4 
Base Model(s)  Qwen/Qwen3.5-122B-A10B   Qwen/Qwen3.5-122B-A10B
Model Size122b
Required VRAM65.4 GB
Updated2026-09-08
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  5.4 GB: 1-of-13   5.3 GB: 2-of-13   5.3 GB: 3-of-13   5.3 GB: 4-of-13   5.3 GB: 5-of-13   5.3 GB: 6-of-13   5.3 GB: 7-of-13   5.3 GB: 8-of-13   5.3 GB: 9-of-13   5.3 GB: 10-of-13   5.3 GB: 11-of-13   5.3 GB: 12-of-13   1.7 GB: 13-of-13
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 122B A10B Mxfp4

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 122B A10B NVFP40K / 83.5 GB24873249
Qwen3.5 122B A10B0K / 248.6 GB2139628605
Qwen3.5 122B A10B0K / 248.6 GB451
Qwen3.5 122B A10B0K / 248.6 GB16808
Qwen3.5 122B A10B Abliterated0K / 248.6 GB585
Qwen3.5 122B A10B FP80K / 126.3 GB1271983112
Qwen3.5 122B A10B NVFP40K / 74 GB1826718
...en3.5 122B A10B Int4 AutoRound0K / 72 GB14231145
AREX Base0K / 164.2 GB54821
Qwen3.5 122B A10B WMix480K / 73.2 GB2153
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.5-122B-A10B-mxfp4.