One RTX 3090 · Strata 6f32ec0 · Qwen3.8 Flash Next IQ3_XXS 76 GB · 3 streams (client-timed)
69.5 tok/sprefill 292 tok/s
qwen3.8-flash-next-iq3_xxs
2026-10-06
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
4 runs, newest first
One RTX 3090 · Strata 6f32ec0 · Qwen3.8 Flash Next IQ3_XXS 76 GB · code review, 1500 tokens
104 tok/sprefill 555 tok/s
Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00001-of-00002.gguf
llama-serverStrata 0.1.39IQ3_XXS177B · 11B activeP538 · G1500 · cache 0%ctx 128krtx-3090linux1 stream! 4 caveats
2026-10-06
Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00001-of-00002.gguf
llama-serverStrata 0.1.39IQ3_XXS177B · 11B activeP33 · G400 · cache 0%ctx 128krtx-3090linux1 stream! 5 caveats
2026-10-06
Qwen3.8-Flash-Next-GSQ-RCO-IQ3_XXS-00001-of-00002.gguf
llama-serverStrata 0.1.39IQ3_XXS177B · 11B activeP33 · G400 · cache 0%ctx 128krtx-3090linux1 stream! 5 caveats
2026-10-06
Page views are counted with Cloudflare Web Analytics: no cookies, no fingerprinting. The toktape binary itself sends nothing anywhere.
