How fast a model would answer on a CPU, before it is fetched
CI / test (push) Failing after 6m37s

Each agent measures its node's memory read rate when it starts: every CPU
sums a share of a buffer past any cache, a tenth of free memory at most,
the best of four passes, in a fraction of a second; reported in Host
(mem_bandwidth_gbs) and NodeView. A token on a CPU reads every weight it
uses once, so one reply's speed is about that rate over those bytes:
modelplan.CPUTokensPerSecond, 0.68 of the measured rate plus 5 ms a token,
calibrated on the PoC against llama.cpp's predicted_per_second (node01
24.9 GB/s, qwen2.5-1.5b: 14.5 measured, 14.7 estimated; node05 41.9 GB/s,
qwen2.5-14b: 3.3 and 3.2). A model of experts named …-A3B reads its active
part (ActiveShare).

The explorer shows it as CPU tok/s, at Q4_K_M on the fastest node that
holds the model; a repository's page gives it for each GGUF by its size.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-27 00:09:47 +01:00
1 parent 2a45068461
commit 84444e71c8
20 files changed
+388 -7

No files matched your search

+6
View File
@@ -93,6 +93,9 @@ type exploreRow struct {
New bool
// Updated is how long ago the repository changed, in the page's language.
Updated string
// CPUSpeed is about how many tokens a second one reply would get on the
// CPU of CPUNode, the fastest node that holds it; empty when unknown.
CPUSpeed, CPUNode string
}
// ParamsLabel is the parameter count as people say it: 7.6B, 494M.
@@ -311,6 +314,9 @@ func (p *AccountPages) exploreList(r *http.Request, d *adminMirrorData) {
e.Hidden++
continue
}
if fit != nil {
row.CPUSpeed, row.CPUNode = fit.rowSpeed(m)
}
if e.Here && row.Verdict.Checked && !row.Verdict.Servable {
e.Hidden++
continue