LLM EXPLORER 57,918 MODELS INDEXED

Qwen3.6 35B A3B Int2 Mixed AutoRound LLMC by Intel

By Intel · 610 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B Int2 Mixed AutoRound LLMC is an open-source language model by Intel. Features: 35b LLM, VRAM: 12.8GB, LLM Explorer Score: 0.3.

  Arxiv:2309.05516   Auto-round Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3...   Compressed-tensors   Conversational   Endpoints compatible   Image-text-to-text   Moe   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Vllm   W2a16   W4a16
Model Card on HF 🤗: https://huggingface.co/Intel/Qwen3.6-35B-A3B-int2-mixed-AutoRound-LLMC 

Qwen3.6 35B A3B Int2 Mixed AutoRound LLMC Parameters and Internals

LLM NameQwen3.6 35B A3B Int2 Mixed AutoRound LLMC
Repository 🤗https://huggingface.co/Intel/Qwen3.6-35B-A3B-int2-mixed-AutoRound-LLMC 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM12.8 GB
Updated2026-08-10
MaintainerIntel
Model Typeqwen3_5_moe
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   2.8 GB: 3-of-3   1.7 GB
Model ArchitectureQwen3_5MoeForConditionalGeneration
Model Max Length262144
Transformers Version5.13.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 35B A3B Int2 Mixed AutoRound LLMC

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 GB2640181475
KAT Coder V2.5 Dev0K / 69.7 GB17885537
Qwen3.6 35B A3B NVFP40K / 23.4 GB8788684482
Qwen AgentWorld 35B A3B0K / 69.2 GB66155665
XYZ Aquila Mini0K / 70.2 GB1760432
Qwen3.6 35B A3B FP80K / 0.8 GB8984811343
Qwen3.6 35B A3B NVFP4 Fast0K / 23.6 GB46366198
Qwen3.6 35B A3B Escha W20K / 12.3 GB3622236
Note: green Score (e.g. "73.2") means that the model is better than Intel/Qwen3.6-35B-A3B-int2-mixed-AutoRound-LLMC.