toktape — published LLM inference runs and their caveats

toktapethe record, not a recording of it

Every run on this page is the file toktape wrote on somebody's own server: the card, the caveats that say when a figure is not quotable, and a replay, all drawn from those same bytes. One word on the machine already running llama-server records yours.

brew install midagedev/tap/toktape other ways to install GitHub

Narrowed toquant: q5_k ×engine: bloomery ×sessions: 1 ×Clear all

1 run, newest first

bloomery · Flint 40B-A2.5B UD-Q4_K_XL (unsloth GGUF) · RTX A6000 · a (unset pick) 78.1 tok/sprefill 824 tok/s

flint-UD-Q4_K_XL.gguf

bloomery0.3.9 (db73b794)q5_KP5342 · G4263 · cache 0%ctx 16krtx-a6000 linux1 stream

midagedev

2026-10-27

Newest first unless you choose another order; there is still no rank column and no score. Every row carries the caveats the card would print, because a result set without them is a leaderboard with the sorting taken out.
toktape publish <run.toktape> puts one here. toktape on GitHub

Page views are counted with Cloudflare Web Analytics: no cookies, no fingerprinting. The toktape binary itself sends nothing anywhere.