Qwen3.6-thinking-coding

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

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

Import

Requires llml ≥ 0.5.0

$ llml import https://llml.dev/profiles/Qwen3.6-thinking-coding.toml --activate

$ brew install --cask flyingnobita/tap/llml

$ llml import https://llml.dev/profiles/Qwen3.6-thinking-coding.toml --activate

$ go install github.com/flyingnobita/llml/cmd/llml@latest

$ llml import https://llml.dev/profiles/Qwen3.6-thinking-coding.toml --activate

$ scoop bucket add flyingnobita https://github.com/flyingnobita/scoop-bucket && scoop install flyingnobita/llml

$ llml import https://llml.dev/profiles/Qwen3.6-thinking-coding.toml --activate

Copy the Run command, paste it in your terminal, and pick a local model. The profile attaches immediately — press p in the TUI to confirm.

Why this profile exists

4-bit quant requires ~23 GB total memory (VRAM + RAM). Tuned for precise coding with lower temperature and no presence penalty.

# args

--temp 0.6

--top-p 0.95

--ctx-size 16384

--top-k 20

--min-p 0.00

--presence-penalty 0.0

--repeat-penalty 1.0

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

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