Qwen3.6

4-bit quant requires ~23 GB total memory (VRAM + RAM).

llama.cpp Mixed Cross-platform General Updated 2026-06-05

Why this profile exists

4-bit quant requires ~23 GB total memory (VRAM + RAM). Thinking disabled via chat-template-kwargs.

# args

--temp 0.7

--top-p 0.8

--ctx-size 16384

--top-k 20

--min-p 0.00

--presence-penalty 1.5

--repeat-penalty 1.0

--chat-template-kwargs {"enable_thinking":false}

Mixed — tested envelope
Cross-platform — backend installed and on PATH
Backend: llama.cpp >= current llml-supported version
Profile assumes the model file is already on disk; llml supplies the path at launch