← ClaudeAtlas

prompting-qwen3-coderlisted

How to prompt and run Qwen3-Coder (qwen3-coder:30b via Ollama) — a NON-thinking model with no deliberation channel, optimised as an agentic patch-writer (though it CAN critique — measured). Covers the official sampling params, tool calling as the vendor's structured path, the 256K/YaRN context story, and the "silent or flooding" failure signature — including the measured finding that a reviewer prompt's own suppression clauses, NOT grammar-forced JSON, silence it. Use when prompting Qwen3-Coder, wiring it into a local council/review seat, debugging an empty or fabricating seat, tuning sampling, or deciding whether it is the right model for a job.
aksheyw/claude-code-learned-skills · ★ 0 · AI & Automation · score 72
Install: claude install-skill aksheyw/claude-code-learned-skills
# Prompting Qwen3-Coder > Source: model card https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct + its `generation_config.json` > + https://github.com/QwenLM/Qwen3-Coder + https://qwenlm.github.io/blog/qwen3-coder/ — snapshot > 2026-07-16, verified against a local Ollama 0.32.0 install. If this snapshot is >60 days old and you're > doing high-stakes work, re-fetch and reconcile. Read the first item before anything else. It is the one that invalidates whole categories of prompt work, and it cost one project four controlled experiments to learn the hard way. --- ## 1. It is a NON-thinking model. There is no deliberation channel. (the big one) Model card, verbatim: > "This model supports only non-thinking mode and does not generate `<think></think>` blocks in its output." Consequences, and they are large: - **`/think`, `/no_think`, and `enable_thinking` do NOT apply.** Those are **Qwen3-general** features. The official Qwen quickstart has no Qwen3-Coder section at all. Sending `think` is not a no-op — qwen-code issue #1377 reports a hard `400: "qwen3-coder:30b" does not support thinking`. - `ollama show qwen3-coder:30b` → `Capabilities: completion, tools`. **No `thinking`.** (Compare gpt-oss:20b, which *does* list `thinking`.) That one command is the fastest way to check this for any model. - **Any prompt that asks it to "think step by step", "reason carefully first", or "take your time" is asking for a channel that does not exist.** It has no exposed thinki