LLM EXPLORER 62,696 MODELS INDEXED

Qwen3.6 35B A3B MLX VQ 2.6bpw by aquaman164

By aquaman164 · 1154 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B MLX VQ 2.6bpw is an open-source language model by aquaman164. Features: 35b LLM, VRAM: 11.5GB, License: apache-2.0, LLM Explorer Score: 0.28.

  4-bit   Aqlm Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3...   Codebook   Conversational   Custom-code   Mixed-bit   Mlx   Moe   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Vq
Model Card on HF 🤗: https://huggingface.co/aquaman164/Qwen3.6-35B-A3B-MLX-VQ-2.6bpw 

Qwen3.6 35B A3B MLX VQ 2.6bpw Parameters and Internals

LLM NameQwen3.6 35B A3B MLX VQ 2.6bpw
Repository 🤗https://huggingface.co/aquaman164/Qwen3.6-35B-A3B-MLX-VQ-2.6bpw 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM11.5 GB
Updated2026-07-19
Maintaineraquaman164
Model Typeqwen3_5_moe
Model Files  5.3 GB: 1-of-3   5.4 GB: 2-of-3   0.8 GB: 3-of-3   0.0 GB
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 35B A3B MLX VQ 2.6bpw

Best Alternatives
Context / RAM
Downloads
Likes
....5 35B A3B Sceptic V3 1M W4A161024K / 26.1 GB2230
...AgentWorld 35B A3B Abliterated256K / 69.2 GB96218
Ornith 1.5 35B A3B NPU2256K /  GB1131
Qwen3.6 35B A3B NPU2256K /  GB960
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 GB1506004506
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
Note: green Score (e.g. "73.2") means that the model is better than aquaman164/Qwen3.6-35B-A3B-MLX-VQ-2.6bpw.