Qwen3.6-27B-mtp

Local LLM 시리즈

1. (Local LLM) Ollama 시작하기
2. Codex 와 Local LLM 연결하기

---

Qwen3.6-27B

1. Qwen 3.6 27B는 로컬 개발의 최적 지점

• https://news.hada.io/topic?id=30942

2. unsloth/Qwen 3.6 27B gguf

• https://huggingface.co/unsloth/Qwen3.6-27B-GGUF

실행 (3080ti)

$ llama-server –help | grep -E “slot|parallel|draft”

llama-server -hf unsloth/Qwen3.6-27B-MTP-GGUF:Q8_0 \
    --spec-type draft-mtp -ngl 999 -fa on -c 65536 --port 8080

Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF

https://huggingface.co/Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF