simongonzalezdc writes about a serving-side tool-attention failure in Qwen3.8-27B via llama-server (jinja templates) where the position of tools in the rendered payload determines whether the model will invoke them. With an 8-tool list, early-positioned, description-less tools were verbally refused as "not wired up" (0/6 success), while the same tools worked perfectly when moved to the tail (3/3) or given a one-line description (6/6). A follow-up with 13 tools confirmed the pattern: a mid-list pair prescribed by name failed 0/5, but tail placement restored 3/3 clean invocation.
- Hypothesis: later tools in the rendered template output receive more attention; compact single-JSON-blob rendering may amplify the position effect versus per-tool natural-language rendering.
- Controlled matrix (24 runs + 27 curl controls) ruled out tool count, context/style, effort level, and fresh-session as causes.
- Test hardware: AMD Strix Halo (gfx1151/HIP) running Q4_K_XL quantization on current llama-server.
- Full methodology and ledgers published in a companion repo: KyaniteLabs/qwen38-27b-strix-halo.
- Hypothesis: later tools in the rendered template output receive more attention; compact single-JSON-blob rendering may amplify the position effect versus per-tool natural-language rendering.
- Controlled matrix (24 runs + 27 curl controls) ruled out tool count, context/style, effort level, and fresh-session as causes.
- Test hardware: AMD Strix Halo (gfx1151/HIP) running Q4_K_XL quantization on current llama-server.
- Full methodology and ledgers published in a companion repo: KyaniteLabs/qwen38-27b-strix-halo.
This guide explains how to use tool calling with local LLMs, including examples with mathematical, story, Python code, and terminal functions, using llama.cpp, llama-server, and OpenAI endpoints.
