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 ×os: macos ×set: prompts@v2 ×Clear all

2 runs, newest first

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 35.6 tok/sprefill 441 tok/s

bloomery0.2.0 (da00c5d4-dirty)q4_KP2249 · G709 · cache 0% · min 706ctx 35koffload partialmacos2 streamsprompts@v2! 6 caveats

midagedev

2026-10-04

GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf 17.9 tok/sprefill 156 tok/s

bloomery0.2.0 (da00c5d4-dirty)q4_KP615 · G368 · cache 0% · min 352ctx 16koffload partialmacos2 streamsprompts@v2! 7 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.