LLM EXPLORER 59,278 MODELS INDEXED

Qwen3.6 35B A3B AWQ by QuantTrio

By QuantTrio · 1020709 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B AWQ is an open-source language model by QuantTrio. Features: 35b LLM, VRAM: 25.5GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.5, ELO: 1395.

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

Qwen3.6 35B A3B AWQ Benchmarks

LMSys ELO 1395 vs 1272 (so35) 9.7%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen3.6 35B A3B AWQ Parameters and Internals

LLM NameQwen3.6 35B A3B AWQ
Repository 🤗https://huggingface.co/QuantTrio/Qwen3.6-35B-A3B-AWQ 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM25.5 GB
Updated2026-08-09
MaintainerQuantTrio
Model Typeqwen3_5_moe
Model Files  3.0 GB: 1-of-9   3.0 GB: 2-of-9   3.0 GB: 3-of-9   3.0 GB: 4-of-9   3.0 GB: 5-of-9   3.0 GB: 6-of-9   3.0 GB: 7-of-9   3.0 GB: 8-of-9   1.5 GB: 9-of-9
AWQ QuantizationYes
Quantization Typeawq
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

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 35B A3B AWQ 4bit0K / 25 GB101078593
Ornith 1.5 35B A3B AWQ INT40K / 24.4 GB20081
Qwen3.6 35B A3B MLX 4bit0K / 20.5 GB5131936
Qwen3.6 35B A3B MLX 6bit0K / 28.9 GB4785922
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB4735371
Qwen3.6 35B A3B UD MLX 4bit0K / 21.6 GB15720112
Nail Qwen3.6 35B A3B MLX 5bit0K / 27.5 GB831
Qwen3.6 35B A3B MLX 8bit0K / 37.8 GB386241
Qwen3.6 35B A3B 6bit0K / 28.9 GB27428
Qwen3.6 35B A3B UD MLX 3bit0K / 17.3 GB229213