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: q4_k_m ×engine: bloomery ×sessions: 2 ×Clear all

2 runs, newest first

Qwen3-30B-A3B-Instruct-2507-Q4_K_M.gguf 38.4 tok/sprefill 5458 tok/s

bloomery0.2.0 (da00c5d4-dirty)Q4_K_MP5875 · G848 · cache 0% · min 834ctx 90kmacos2 streamsprompts@v2 ! 6 caveats

midagedev

2026-10-04

Qwen3-30B-A3B-Instruct-2507-Q4_K_M.gguf 42.7 tok/sprefill 6003 tok/s

bloomery0.2.0 (da00c5d4-dirty)Q4_K_MP5875 · G929 · cache 0% · min 898ctx 48kmacos2 streamsprompts@v2 ! 6 caveats

midagedev

2026-10-04

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.