LLM EXPLORER 60,783 MODELS INDEXED

Qwen3.5 122B A10B Vision MLX Mixed 4bit by andrzejmontano

By andrzejmontano · 44 downloads
HF Repo ↗ Copy URL

Qwen3.5 122B A10B Vision MLX Mixed 4bit is an open-source language model by andrzejmontano. Features: 122b LLM, VRAM: 4.7GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.23.

  4bit Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-122b-a...   Conversational   Image-text-to-text   Mlx   Quantized   Qwen   Qwen3 5 moe   Region:us   Vision
Model Card on HF 🤗: https://huggingface.co/andrzejmontano/Qwen3.5-122B-A10B-Vision-MLX-Mixed-4bit 

Qwen3.5 122B A10B Vision MLX Mixed 4bit Parameters and Internals

LLM NameQwen3.5 122B A10B Vision MLX Mixed 4bit
Repository 🤗https://huggingface.co/andrzejmontano/Qwen3.5-122B-A10B-Vision-MLX-Mixed-4bit 
Base Model(s)  Qwen/Qwen3.5-122B-A10B   Qwen/Qwen3.5-122B-A10B
Model Size122b
Required VRAM4.7 GB
Updated2026-06-15
Maintainerandrzejmontano
Model Typeqwen3_5_moe
Model Files  5.5 GB   5.7 GB   5.7 GB   5.5 GB   5.7 GB   5.7 GB   5.5 GB   5.7 GB   5.7 GB   5.5 GB   5.7 GB   5.7 GB   5.5 GB   4.7 GB
Quantization Type4bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 122B A10B Vision MLX Mixed 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 122B A10B 8bit0K / 129.7 GB41242
Qwen3.5 122B A10B 4bit0K / 69.5 GB1441219
Qwen3.5 122B A10B OptiQ 2bit0K / 46.1 GB10934
Qwen3.5 122B A10B 6bit0K / 100.1 GB38463
...3.5 122B A10B GameDev MLX 4bit0K / 44.4 GB2304
Qwen3.5 122B A10B 5bit0K / 85.2 GB6542
Qwen3.5 122B A10B 6bit Gs320K / 107.9 GB1001
Qwen3.5 122B A10B NVFP40K / 83.5 GB24873249
Qwen3.5 122B A10B0K / 248.6 GB2139628605
Qwen3.5 122B A10B0K / 248.6 GB451
Note: green Score (e.g. "73.2") means that the model is better than andrzejmontano/Qwen3.5-122B-A10B-Vision-MLX-Mixed-4bit.