LLM EXPLORER 55,709 MODELS INDEXED

Qwen3.6 35B A3B AWQ 4bit by cyankiwi

By cyankiwi · 1010785 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B AWQ 4bit is an open-source language model by cyankiwi. Features: 35b LLM, VRAM: 25GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.38.

  4-bit   4bit   Awq Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3...   Conversational   Deploy:azure   Endpoints compatible   Image-text-to-text   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit 

Qwen3.6 35B A3B AWQ 4bit Parameters and Internals

LLM NameQwen3.6 35B A3B AWQ 4bit
Repository 🤗https://huggingface.co/cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM25 GB
Updated2026-08-08
Maintainercyankiwi
Model Typeqwen3_5_moe
Model Files  5.0 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   4.1 GB: 4-of-6   5.0 GB: 5-of-6   0.9 GB: 6-of-6
AWQ QuantizationYes
Quantization Typeawq|4bit
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 AWQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B 4bit0K / 20.5 GB6203692
Qwen3.6 35B A3B 8bit0K / 37.8 GB12017527
Qwen3.6 35B A3B OptiQ 4bit0K / 22.1 GB1473044
...ugHunter RATH Mlx 4bit Mtp Msq0K / 22.5 GB27697
... 4.7 Opus Abliterated Mlx 8bit0K / 37 GB765227
Ornith 1.0 35B UD Q2 K XL MLX0K / 13.3 GB15970
...er BugHunter RATH Mlx 4bit Msq0K / 21.6 GB17282
Qwen3.6 35B A3B 4bit DWQ0K / 20.7 GB408816
Ornith 1.0 35B UD Q8 K XL Mlx0K / 37.9 GB7373
...B Abliterated Heretic MLX 4bit0K / 24.5 GB242819