2026-09-06 12:03 UTC
Rerunning the experiment with Qwen3.8-Flash-Next 125b on the same 128GB Strix Halo machine yields an even better result: a Rust port with full feature parity in only 4 hours and only 3 compactions.
262k q8_0 context, Vulkan, low reasoning, preserve thinking.
https://mas.to/@prutser/117223965735698905
Replies (1)
-
@prutser@mas.to 2026-09-06 12:04
The compaction saw tooths are nicely visible.