# Gemini 4 Neon wrote AMD kernels that nearly doubled Inkling 2 Mini decode speed in 4.3 hours

> Source: <https://runtimewire.com/article/gemini-4-neon-wrote-amd-kernels-that-nearly-doubled-inkling-2-mini-decode-speed>
> Published: 2026-11-22 01:50:37+00:00

**Recommendation:** On new AMD hardware with nascent ROCm support, have a coding agent generate custom Loom kernels rather than relying on llama.cpp defaults; the source measured 44.8 vs 23.8 tokens/s decode and 5.9x prefill at 18k tokens.
More in the playbook "Inference and self-hosting": <https://wpnews.pro/playbooks/inference-serving>

# Gemini 4 Neon wrote AMD kernels that nearly doubled Inkling 2 Mini decode speed in 4.3 hours

**The agent-built Loom package also hit 5.9x llama.cpp prefill at an 18k-token prompt, against day-one support the AMD engineer called super nascent.**

        By [Ryan Merket](https://runtimewire.com/author/ryan-merket)
        · Published 

An AMD engineer used Gemini 4 Neon to port Thinking Machines Lab's Inkling 2 Mini to a Strix Halo machine in about 4.3 hours, producing custom Loom kernels that ran decode at 44.8 tokens per second against 23.8 tokens per second for llama.cpp on ROCm.…
