Alibaba

Qwen3.6 27B

27,8B

Parameters

16,7 Go

Q4_K_M file

≥ 18,2 Go

Recommended VRAM

262 144

Max context

Not measured yet

No card has run the TokenBench protocol on this model yet. The current protocol covers a selection of models; benchmarking any catalog model from the app is coming soon.

Measure my card →

Which cards should it fit on?

Cards on the site whose video memory covers the recommended 18,2 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published: 2026-04-21
Architecture: 64 layers · 4 KV heads · dimension 256
Attention: Hybrid: 16 of 64 layers use standard attention, the others a fixed-memory mechanism (Mamba, linear attention) — a very light cache.
Context cache (f16): ≈ 63 MB per 1,000 tokens · 2,0 Go for 32,768 tokens
GGUF file: bartowski/Qwen_Qwen3.6-27B-GGUF · Qwen_Qwen3.6-27B-Q4_K_M.gguf Download (16,7 Go)
Official repo: Qwen/Qwen3.6-27B

Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.