nvidia-nemotron3-nano-4b
155 tok/sprefill 161 tok/s
bloomery0.3.3 (5626a09692a8e53418bd629c9d8f5b8720822f98)q5_0P1222 · G3475 · cache 0%ctx 256krtx-3090linux1 streamprompts@v2! 1 caveat
2026-10-15
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
10 runs, newest first
nvidia-nemotron3-nano-4b
156 tok/sprefill 162 tok/s
bloomery0.3.2 (ba35fde3)q5_0P1233 · G3486 · cache 0%ctx 256krtx-3090linux1 streamprompts@v2! 1 caveat
2026-10-15
Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf
31.6 tok/sprefill 954 tok/s
juliankang4 anonymous
2026-10-12
qwen3.6-35b-a3b
86.9 tok/sprefill 4301 tok/s
juliankang4 anonymous
2026-10-12
qwen3.8-35b-a3b
56.3 tok/sprefill 145 tok/s
anonymous
2026-10-11
qwen3.6-35b-a3b
69.1 tok/sprefill 3999 tok/s
juliankang4 anonymous
2026-10-11
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
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
2026-10-04
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
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
2026-10-04
Page views are counted with Cloudflare Web Analytics: no cookies, no fingerprinting. The toktape binary itself sends nothing anywhere.
