LLM EXPLORER 58,608 MODELS INDEXED

Qwen3.6 35B A3B OQ2e MTP MLX by treeish

By treeish · 13 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B OQ2e MTP MLX is an open-source language model by treeish. Features: 35b LLM, VRAM: 13.6GB, License: apache-2.0.

  2-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3...   Conversational   Image-text-to-text   Imatrix   Mlx   Mtp   Oq   Oqe   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Sprig   Tensorflow   Treeish
Model Card on HF 🤗: https://huggingface.co/treeish/Qwen3.6-35B-A3B-oQ2e-MTP-MLX 

Qwen3.6 35B A3B OQ2e MTP MLX Parameters and Internals

LLM NameQwen3.6 35B A3B OQ2e MTP MLX
Repository 🤗https://huggingface.co/treeish/Qwen3.6-35B-A3B-oQ2e-MTP-MLX 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM13.6 GB
Updated2026-08-17
Maintainertreeish
Model Typeqwen3_5_moe
Model Files  5.1 GB: 1-of-3   5.0 GB: 2-of-3   3.5 GB: 3-of-3
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 OQ2e MTP MLX

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B0K / 72.2 GB55408552648
Qwen3.5 35B A3B0K / 72.3 GB21585111482
Ornith 1.0 35B0K / 70.4 GB3211614498
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
KAT Coder V2.5 Dev0K / 69.7 GB17885537
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
Qwen3.6 35B A3B NVFP4 Fast0K / 23.6 GB46366198
XYZ Aquila Mini0K / 70.2 GB1760432
Ornith 1.0 35B FP80K / 37.4 GB85224081
Note: green Score (e.g. "73.2") means that the model is better than treeish/Qwen3.6-35B-A3B-oQ2e-MTP-MLX.