--- license: apache-2.0 tags: - chat-template - qwen3 - tool-calling --- # froggeric-terse-coder — chat template for Qwen3.8 Terse-Coder The recommended chat template for the [Terse-Coder](https://huggingface.co/Shockem/Qwen3.8-27b-Terse-Coder) family (also bundled inside each model repo as `chat_template.jinja`). Lineage: derived from [froggeric/Qwen-Fixed-Chat-Templates](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates) — the house `qwen3.8-froggeric-v5` template, tuned for terse-reasoning models. It is what our benchmarks and the daily driver run — serving the model without it (or with a scaffold that overrides the system prompt) changes behavior, most noticeably around **tool-call discipline**: - Anti-rumination rules: after a tool error, do not repeat the same command and do not announce retries. - `reasoning_effort: high` maps to the model's extended thinking tier; default thinking is on. - Tool calls use the qwen3_coder format (``), parsed natively by vLLM (`qwen3_coder_mcp`), SGLang, and TabbyAPI. - Completed-turn `` content is not replayed unless `preserve_thinking` is set. ## Usage vLLM: ```bash vllm serve Shockem/Qwen3.8-27b-Terse-Coder-NVFP4 \ --chat-template chat_template.jinja \ --speculative-config '{"method":"mtp","num_speculative_tokens":3}' ``` llama.cpp: ```bash llama-server -m Qwen3.8-27b-Terse-Coder.Q4_K_M.gguf \ --chat-template chat_template.jinja -ngl 99 ``` SGLang: ```bash sglang serve --model-path Shockem/Qwen3.8-27b-Terse-Coder-NVFP4 \ --chat-template chat_template.jinja ``` Note: the think-budget ladder (caps per `reasoning_effort` level) is applied server-side in our deployment, not by the template itself — see the model cards for the measured setup. Licensed Apache 2.0.