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: iq2_xxs ×engine: llama-server ×os: linux ×Clear all

2 runs, newest first

llama.cpp llama-server · Nemotron 3.5 Bolt 74B-A9B · RTX 3090 alone · 5.7K-token prompt 76.8 tok/sprefill 1917 tok/s

hf-packed-345x8.1b

llama-serverb11668IQ2_XXS74B · 72B activeP5680 · G361 · cache 0%ctx 16kfa onrtx-3090 rtx-a6000linux1 stream ! 2 caveats

midagedev

2026-10-17

llama.cpp llama-server · Nemotron 3.5 Bolt 74B-A9B · RTX A6000 alone · 5.7K-token prompt 79.9 tok/sprefill 2170 tok/s

hf-packed-345x8.1b

llama-serverb11668IQ2_XXS74B · 72B activeP5680 · G395 · cache 0%ctx 16kfa onrtx-3090 rtx-a6000linux1 stream ! 2 caveats

midagedev

2026-10-17

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.