LLM EXPLORER 62,007 MODELS INDEXED

Qwen3.6 35B A3B MXFP6 by nekofish

By nekofish · 38 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B MXFP6 is an open-source language model by nekofish. Features: 35b LLM, VRAM: 29.3GB, License: apache-2.0, LLM Explorer Score: 0.3.

  8-bit   Conversational   Endpoints compatible   Image-text-to-text   Quark   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nekofish/Qwen3.6-35B-A3B-MXFP6 

Qwen3.6 35B A3B MXFP6 Parameters and Internals

LLM NameQwen3.6 35B A3B MXFP6
Repository 🤗https://huggingface.co/nekofish/Qwen3.6-35B-A3B-MXFP6 
Model Size35b
Required VRAM29.3 GB
Updated2026-09-23
Maintainernekofish
Model Typeqwen3_5_moe
Model Files  2.3 GB: 1-of-26   0.9 GB: 2-of-26   1.3 GB: 3-of-26   1.3 GB: 4-of-26   1.3 GB: 5-of-26   1.6 GB: 6-of-26   0.4 GB: 7-of-26   1.5 GB: 8-of-26   0.4 GB: 9-of-26   1.5 GB: 10-of-26   0.4 GB: 11-of-26   1.3 GB: 12-of-26   0.6 GB: 13-of-26   1.3 GB: 14-of-26   0.6 GB: 15-of-26   1.5 GB: 16-of-26   0.4 GB: 17-of-26   1.5 GB: 18-of-26   0.4 GB: 19-of-26   1.3 GB: 20-of-26   0.6 GB: 21-of-26   1.3 GB: 22-of-26   1.3 GB: 23-of-26   1.3 GB: 24-of-26   1.5 GB: 25-of-26   1.5 GB: 26-of-26
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 35B A3B MXFP6

Best Alternatives
Context / RAM
Downloads
Likes
...AgentWorld 35B A3B Abliterated256K / 69.2 GB96218
Ornith 1.5 35B A3B NPU2256K /  GB1291
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
Ornith 1.0 35B0K / 70.4 GB1630944506
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
KAT Coder V2.5 Dev0K / 69.7 GB17885537
Qwen3.8 35B A3B Distill0K / 69.9 GB353249
Note: green Score (e.g. "73.2") means that the model is better than nekofish/Qwen3.6-35B-A3B-MXFP6.