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

/

Narrow by model, size, engine, quantisation, GPU, host, VRAM, prompt set

Narrowed toengine: bloomery ×os: linux ×Clear all

91 runs, newest first · showing the first 30

qwen3.6-35b-a3b 86.9 tok/sprefill 4301 tok/s

bloomery0.3.0 (8d937828)P7261 · G1590 · cache 0%ctx 256kgb10linux1 stream prompts@v2 ! 1 caveat

juliankang4 anonymous

2026-10-12

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 54.0 tok/sprefill 449 tok/s

bloomery0.3.0 (8d937828)q4_KP3903 · G256 · cache 0%ctx 7680offload partialrtx-5090linux1 stream

anonymous

2026-10-12

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 46.5 tok/sprefill 124 tok/s

bloomery0.3.0 (8d937828)q4_KP32 · G256 · cache 0%ctx 7680offload partialrtx-5090linux1 stream ! 1 caveat

anonymous

2026-10-12

qwen3.6-35b-a3b 346 tok/sprefill 14952 tok/s

bloomery0.3.0 (8d937828)P4028 · G256 · cache 0%ctx 222krtx-5090linux1 stream

anonymous

2026-10-12

qwen3.6-35b-a3b 356 tok/sprefill 1662 tok/s

bloomery0.3.0 (8d937828)P32 · G256 · cache 0%ctx 222krtx-5090linux1 stream ! 1 caveat

anonymous

2026-10-12

GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf 28.9 tok/sprefill 169 tok/s

bloomery0.2.10 (8e55b8ce)q4_KP2067 · G149 · cache 33% · min 79ctx 16koffload partialrtx-a6000linux1 stream ! 2 caveats

midagedev

2026-10-11

GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf 27.9 tok/sprefill 139 tok/s

bloomery0.3.0 (8d937828)q4_KP2067 · G159 · cache 50% · min 84ctx 16koffload partialrtx-a6000linux1 stream ! 3 caveats

midagedev

2026-10-11

qwen3.8-35b-a3b 56.3 tok/sprefill 145 tok/s

bloomery0.2.10 (8e55b8ce)P1464 · G400 · cache 0%ctx 2krtx-3060linux1 stream prompts@v2 ! 1 caveat

anonymous

2026-10-11

qwen3.6-35b-a3b 69.1 tok/sprefill 3999 tok/s

bloomery0.2.10 (unknown)P7257 · G1256 · cache 0%ctx 128kgb10linux1 stream prompts@v2 ! 2 caveats

juliankang4 anonymous

2026-10-11

Cloudflare_clef-flash-Q4_K_M.gguf 215 ms p50engine 212 ms

decision modelbloomery0.2.10 (unknown)Q4_K_M gb10linux! 1 caveat

juliankang4 anonymous

2026-10-11

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 81.9 tok/s

bloomery0.2.10 (8e55b8ce)q4_KP33 · G400 · cache 0%ctx 8koffload partialrtx-3090 rtx-a6000linux2 streams ! 2 caveats

midagedev

2026-10-10

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 88.9 tok/s

bloomery0.2.10 (8e55b8ce)q4_KP33 · G400 · cache 0%ctx 8koffload partialrtx-a6000linux2 streams ! 2 caveats

midagedev

2026-10-10

qwen3.6-35b-a3b 177 tok/s

bloomery0.2.10 (8e55b8ce)UD-Q4_K_XLP33 · G400 · cache 0%ctx 8krtx-a6000linux2 streams ! 1 caveat

midagedev

2026-10-10

GLM-5.3-Flash-UD-IQ4_XS-00001-of-00005.gguf 24.6 tok/s

bloomery0.2.10 (8e55b8ce)iq3_sP38 · G400 · cache 0%ctx 8koffload partialrtx-a6000linux2 streams ! 4 caveats

midagedev

2026-10-10

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 93.8 tok/s

bloomery0.2.10 (8e55b8ce)q4_KP33 · G400 · cache 0%ctx 16koffload partialrtx-3090 rtx-a6000linux1 stream ! 1 caveat

midagedev

2026-10-10

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 97.6 tok/s

bloomery0.2.10 (8e55b8ce)q4_KP33 · G400 · cache 0%ctx 16koffload partialrtx-3090 rtx-a6000linux1 stream ! 1 caveat

midagedev

2026-10-10

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 103 tok/sprefill 1312 tok/s

bloomery0.2.10 (8e55b8ce)q4_KP538 · G1500 · cache 0%ctx 16koffload partialrtx-3090 rtx-a6000linux1 stream

midagedev

2026-10-10

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 77.9 tok/sprefill 1698 tok/s

bloomery0.2.10 (8e55b8ce)q4_KP5673 · G387 · cache 0%ctx 16koffload partialrtx-3090 rtx-a6000linux1 stream

midagedev

2026-10-10

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 90.8 tok/s

bloomery0.2.10 (8e55b8ce)q4_KP33 · G400 · cache 0%ctx 16koffload partialrtx-a6000linux1 stream ! 1 caveat

midagedev

2026-10-10

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 94.1 tok/sprefill 1001 tok/s

bloomery0.2.10 (8e55b8ce)q4_KP538 · G1500 · cache 0%ctx 16koffload partialrtx-a6000linux1 stream

midagedev

2026-10-10

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf 70.9 tok/sprefill 1577 tok/s

bloomery0.2.10 (8e55b8ce)q4_KP5673 · G469 · cache 0%ctx 16koffload partialrtx-a6000linux1 stream

midagedev

2026-10-10

qwen3.6-35b-a3b 118 tok/s

bloomery0.2.10 (8e55b8ce)UD-Q4_K_XLP33 · G400 · cache 0%ctx 16krtx-a6000linux1 stream ! 1 caveat

midagedev

2026-10-10

qwen3.6-35b-a3b 115 tok/sprefill 7108 tok/s

bloomery0.2.10 (8e55b8ce)UD-Q4_K_XLP5673 · G534 · cache 0%ctx 16krtx-a6000linux1 stream

midagedev

2026-10-10

MiMo-V2.6-Flash-MOPD-MXFP4-00001-of-00002.gguf 19.5 tok/s

bloomery0.2.10 (8e55b8ce)mxfp4P30 · G400 · cache 0%ctx 16koffload partialrtx-a6000linux1 stream ! 2 caveats

midagedev

2026-10-10

MiMo-V2.6-Flash-MOPD-MXFP4-00001-of-00002.gguf 19.1 tok/sprefill 84.4 tok/s

bloomery0.2.10 (8e55b8ce)mxfp4P5620 · G480 · cache 0%ctx 16koffload partialrtx-a6000linux1 stream

midagedev

2026-10-10

GLM-5.3-Flash-UD-IQ4_XS-00001-of-00005.gguf 25.1 tok/s

bloomery0.2.10 (8e55b8ce)iq3_sP33 · G400 · cache 0%ctx 16koffload partialrtx-a6000linux1 stream ! 3 caveats

midagedev

2026-10-10

GLM-5.3-Flash-UD-IQ4_XS-00001-of-00005.gguf 24.6 tok/sprefill 106 tok/s

bloomery0.2.10 (8e55b8ce)iq3_sP5548 · G600 · cache 0%ctx 16koffload partialrtx-a6000linux1 stream ! 1 caveat

midagedev

2026-10-10

bloomery 0.2.6 · Qwen3.8 Flash UD-Q4_K_XL · A6000 + 3090 · 3.8K-token prompt, MTP 83.8 tok/sprefill 1450 tok/s

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf

bloomery0.2.6 (39b13149)q4_KP3847 · G425 · cache 0%ctx 8koffload partialrtx-3090 rtx-a6000linux1 stream

midagedev

2026-10-07

One RTX 3090 · bloomery 0.2.1 · Qwen3.8 Flash Next UD-Q4_K_XL 111 GB · code review, 1500 tokens 71.9 tok/sprefill 461 tok/s

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf

bloomery0.2.1 (b83f1269)q4_KP538 · G1500 · cache 0%ctx 38koffload partialrtx-3090linux1 stream ! 1 caveat

midagedev

2026-10-06

One RTX 3090 · bloomery 0.2.1 · Qwen3.8 Flash Next UD-Q4_K_XL 111 GB · Korean chat 57.3 tok/s

Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf

bloomery0.2.1 (b83f1269)q4_KP33 · G400 · cache 0%ctx 38koffload partialrtx-3090linux1 stream ! 2 caveats

midagedev

2026-10-06

Older runs →

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.