Codeman

0 Fork 0

mirror of https://github.com/Ark0N/Codeman.git synced 2026-11-14 02:29:33 +01:00

Files

T

Codeman maintainer 4423949923 fix(local-model): the MLX row of Muse Glimmer takes a 5 GB peak, and says what was compared

Three corrections to the row added in 5396e33b, none of which changes where it is offered:

- Its peak. The run gave the process footprint's LIFETIME maximum, read at the end: 3.0 to
  3.3 GB above what was held then. That is a floor, because a larger transient during the
  earlier, longer prompts would not show in it. The row now takes the first measured row's
  5 GB: 36.1 GB at 65,536 tokens (0.960 of a 48 GB Mac's estimate) and 39.0 GB at 131,072
  (0.972 of what that Mac's runtime measures).
- What was compared. The two builds were not given the same prompt in OpenCode: the GGUF
  build got a one-line task through the skill's sendmark (which adds its answer-file
  sentence), the MLX build a plain one-line prompt. And the speeds to set side by side are
  the two from the same 300-token request, 15.2 and 30.2.
- Runtime issue 18269: whether the memory fix its maintainer promised predates the pinned
  runtime is not known, and the header says so.

Also a stale comment: the catalogue holds eleven models.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

2026-11-12 03:02:08 +01:00

connect.ts

fix(local-model): claim the connection first, keep an outcome the disk refused, say why a start failed

2026-11-06 23:54:45 +01:00

developer-tools.ts

feat(local-model): the pinned runtime, its supervisor and the runtime client

2026-11-06 22:16:38 +01:00

format.ts

feat(local-model): judge the fit on the measured peak and rank a tested Mac first

2026-11-06 22:16:37 +01:00

hardware.ts

feat(local-model): hardware probe, model catalogue and the pure recommendation