6GB GPU 上同一款本地模型的 3 個編碼 Agent 測試：pi、Codex 各 12/12，Claude Code 7/12

Claude Code told me the web page was done. The folder was empty.

That was the worst moment of a small test: one local model on a 6GB laptop GPU, plugged into three coding agents. Same model, same tasks. Only the agent changed.

Setup

• RTX 3060 Laptop 6GB + 64GB RAM, WSL2 Ubuntu 24.04
• llama.cpp 9655061: llama-server -c 32768 -ngl 99 -fa on -ctk q8_0 -ctv q8_0 --jinja; experts on CPU (-ncmoe 36 for LFM, -ncmoe 40 for Qwen). Fully offline.
• Models: LFM2.5-24B-A2B Q4_0 (3 runs per task), Qwen3.6-35B-A3B UD-Q4_K_XL (1 run, control)
• Tasks:
  • A: fix two bugs in calc.py until pytest passes
  • B: single-file timer page, checked by a script against 8 items
  • Pelican: Generate an SVG of a pelican riding a bicycle
• 900 s cap per run

Results

The prompt is the problem

Every request starts with the agent's system prompt and tool definitions. First prompt eval in the llama-server log:

With a 32K context, Claude Code fills about half of it before doing anything, and reading that prompt takes about 8.6× longer than pi's.

pi

12/12 on both models, zero tool errors in the logs, fastest bug fix (47 s median). I also trimmed its prompt to about 750 tokens with only read/edit/bash enabled. Still 12/12, same speed. Harder tasks might separate the two; these didn't.

Codex

12/12, but LFM made 12 tool-argument errors, mostly integers sent as strings:

failed to parse function arguments: invalid type: string "96787", expected i32

It retries and recovers. The cost is time: 85 s median for the bug fix, 599 s on the first run.

Claude Code

• LFM passed the bug fix once in three runs. The other two died with:

  Prompt is too long · automatic compaction failed: summarization produced empty response

• Timer page: 3/3, but an 881 s median, and one run hit the 900 s cap.
• Qwen: 0/3. For the page and the pelican it replied that the task was complete. The working folder had no files.

An error tells you something failed. A false "done" only shows up when you check the folder yourself.

Pelicans

Called directly, LFM's pelican floats above the bike; inside an agent it actually sits on it. Qwen's drawings are more complete. Claude Code + Qwen produced no SVG.

Takeaways

• Small local model, small context: pick the agent with the smallest prompt. Here that was pi, then Codex.
• If you must use Claude Code locally, give it more context (Ollama's docs suggest 64K+) and look at Unsloth's notes on trimming its prompt (--bare). I didn't test those here.
• Always ls after an agent says it's done.

Limits

• VRAM was sampled once per second, so I only saw resident usage (~2,641 MiB LFM, ~3,111 MiB Qwen), not peaks.
• Tool-error counts come from log keyword matching and are approximate.
• Qwen got one run per task.
• Three small tasks, not a real project.

Full data and configs: https://kunbuilds.com/en/posts/agents-local-model-6gb/

Sources

• Ollama, Claude Code integration: https://docs.ollama.com/integrations/claude-code
• Unsloth, Claude Code with local LLMs: https://unsloth.ai/docs/basics/claude-code