LLM EXPLORER 64,069 MODELS INDEXED

Qwen3.6 35B A3B W8a8 Llmcompressor by amd

By amd · 2265 downloads
HF Repo ↗ Copy URL

Qwen3.6 35B A3B W8a8 Llmcompressor is an open-source language model by amd. Features: 35b LLM, VRAM: 37.7GB, License: apache-2.0, LLM Explorer Score: 0.29.

  8-bit   Amd Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3...   Compressed-tensors   Conversational   Cpu-inference   Dynamic-quantization   En   Endpoints compatible   Image-text-to-text   Int8   Llm-compressor   Quantized   Qwen3 5 moe   Region:us   Safetensors   W8a8   Zendnn
Model Card on HF 🤗: https://huggingface.co/amd/Qwen3.6-35B-A3B-w8a8-llmcompressor 

Qwen3.6 35B A3B W8a8 Llmcompressor Parameters and Internals

LLM NameQwen3.6 35B A3B W8a8 Llmcompressor
Repository 🤗https://huggingface.co/amd/Qwen3.6-35B-A3B-w8a8-llmcompressor 
Base Model(s)  Qwen/Qwen3.6-35B-A3B   Qwen/Qwen3.6-35B-A3B
Model Size35b
Required VRAM37.7 GB
Updated2026-08-27
Maintaineramd
Model Typeqwen3_5_moe
Model Files  37.7 GB
Supported Languagesen
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.10.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 35B A3B W8a8 Llmcompressor

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 /  GB780
Qwen3.6 35B A3B NPU2256K /  GB880
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 GB1417207506
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 amd/Qwen3.6-35B-A3B-w8a8-llmcompressor.