LLM EXPLORER 56,604 MODELS INDEXED

Qwen3.5 122B A10B WMix48 by WinterCharm

By WinterCharm · 215 downloads
HF Repo ↗ Copy URL

Qwen3.5 122B A10B WMix48 is an open-source language model by WinterCharm. Features: 122b LLM, VRAM: 73.2GB, License: apache-2.0.

  Arxiv:2210.17323   4-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-122b-a...   Conversational   Image-text-to-text   Mlx   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Winter-mix
Model Card on HF 🤗: https://huggingface.co/WinterCharm/Qwen3.5-122B-A10B-wMix48 

Qwen3.5 122B A10B WMix48 Parameters and Internals

LLM NameQwen3.5 122B A10B WMix48
Repository 🤗https://huggingface.co/WinterCharm/Qwen3.5-122B-A10B-wMix48 
Base Model(s)  Qwen/Qwen3.5-122B-A10B   Qwen/Qwen3.5-122B-A10B
Model Size122b
Required VRAM73.2 GB
Updated2026-08-09
MaintainerWinterCharm
Model Typeqwen3_5_moe
Model Files  5.2 GB: 1-of-14   5.4 GB: 2-of-14   5.3 GB: 3-of-14   5.3 GB: 4-of-14   5.3 GB: 5-of-14   5.4 GB: 6-of-14   5.0 GB: 7-of-14   5.3 GB: 8-of-14   5.3 GB: 9-of-14   5.4 GB: 10-of-14   5.4 GB: 11-of-14   5.0 GB: 12-of-14   5.3 GB: 13-of-14   4.6 GB: 14-of-14
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 WMix48

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 122B A10B NVFP40K / 83.5 GB24873249
Qwen3.5 122B A10B Abliterated0K / 248.6 GB495
...en3.5 122B A10B Int4 AutoRound0K / 72 GB14231145
Qwen3.5 122B A10B OQ4 Mtp0K / 72.5 GB9253
Qwen3.5 122B A10B Bf160K / 224.2 GB27732
Qwen3.5 REAP 97B A10B0K / 194.2 GB3117
Qwen3.5 122B A10B SFT0K / 11.6 GB291
Qwen3.5 122B A10B WMix580K / 87.5 GB2143
Qwen3.5 122B A10B WMix680K / 102.1 GB1561
Qwen3.5 122B A10B FP80K / 126.3 GB1271983112
Note: green Score (e.g. "73.2") means that the model is better than WinterCharm/Qwen3.5-122B-A10B-wMix48.