local-llm
- Image input on a 27B coder costs 1.1 GiB, once
Image input for Qwen3.8-27B coding keys on an RTX 3090 cost 1.1 GiB at load on every variant. A full 121k-token context with a screenshot added 118 MiB.
- One open PR made MoE prompts 12-30% faster on my 3090
115 llama.cpp commits gave my RTX 3090 2.8% at most. One open PR from Unsloth's fork made MoE prompts 21-30% faster in llama-bench, 12-13% in llama-server.
- The screenshot opencode never sent
Local vision models on a Radeon 680M read test screenshots almost perfectly. Three opencode versions sent an error string instead until one config key was set.
- OpenCode didn't want an account. It wanted a model name.
A forwarded warning said OpenCode 2.x needs an opencode.ai account for self-hosted models. It doesn't. It needs you to name the model.
- My agent guardrails passed every test. Then I used them.
Weeks of tests against a scripted fake model, then one evening of real work with my coding-agent templates: three complaints, six findings.
- Lock OpenCode 2.x to your self-hosted model
Stop OpenCode 2.x from picking its hosted free model: name your local model or disable the opencode provider, then prove it with a PoC script.
- Eighteen days later, the same lie
A 122B model promised an atomic Java transfer it never wrote. Eighteen days later it did it again: all 4 new Java cells, 6 of 6 across both runs.
- 115 llama.cpp commits later, my 3090 was barely faster
I checked 115 new llama.cpp commits on an RTX 3090: tool calls held, speed moved 2.8% at most, adaptive MTP gave nothing. I switched anyway.
- Faster prompts, slower agents: a second engine on the 680M
A MoE engine read prompts 1.4x faster than llama.cpp on a Radeon 680M and generated slower. Three agent runs got the same grades and finished later.
- The template differed. The prompts didn't.
Two quants of one 122B model shipped two chat templates. I held the template equal, then checked whether it had ever mattered.