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 ×sessions: 1 ×Clear all

78 runs, newest first · showing the first 30

bloomery · Mistral Large 4 1T-A52B UD-IQ1_S (unsloth GGUF) · RTX 3090 alone · a (unset pick) · 한국어 질문 10.6 tok/sprefill 24.5 tok/s

mistral-large-4-1t-a52b

bloomery0.3.12 (2cd109a602c4)iq1_sP72 · G1444 · cache 14%ctx 50koffload partialrtx-3090 rtx-a6000linux1 stream! 2 caveats

midagedev

2026-11-03

bloomery · Flint 40B-A2.5B UD-Q4_K_XL (unsloth GGUF) · RTX A6000 · a (unset pick) 78.1 tok/sprefill 824 tok/s

flint-UD-Q4_K_XL.gguf

bloomery0.3.9 (db73b794)q5_KP5342 · G4263 · cache 0%ctx 16krtx-a6000linux1 stream

midagedev

2026-10-27

bloomery · MiniMax-M3.1-Flash UD-Q2_K_XL (unsloth GGUF) · RTX A6000 + RTX 3090 · bp (unset pick) 29.7 tok/sprefill 162 tok/s

MiniMax-M3.1-Flash-UD-Q2_K_XL-00001-of-00004.gguf

bloomery0.3.9 (68b92a92-dirty)iq2_xsP5617 · G1500 · cache 0%ctx 16koffload partialrtx-3090 rtx-a6000linux1 stream

midagedev

2026-10-27

bloomery 0.3.9 candidate · Muse Spark Open 816B-A42B UD-IQ2_XXS · RTX A6000 + RTX 3090 · bp (unset pick) 14.2 tok/sprefill 94.4 tok/s

muse-spark-open-816b-a42b

bloomery0.3.8 (37e06f5f)iq2_xxsP5554 · G600 · cache 0%ctx 16koffload partialrtx-3090 rtx-a6000linux1 stream! 1 caveat

midagedev

2026-10-24

bloomery 0.3.9 candidate · MiniMax-M3.1-Flash (native NVFP4 safetensors) · RTX A6000 + RTX 3090 · bp (unset pick) 15.8 tok/sprefill 98.3 tok/s

MiniMax-M3.1-Flash

bloomery0.3.8 (3233ba8d-dirty)nvfp4_rowsP5617 · G600 · cache 0%ctx 16koffload partialrtx-3090 rtx-a6000linux1 stream! 1 caveat

midagedev

2026-10-24

bloomery 0.3.9 candidate · MiniMax-M3.1-Flash (native NVFP4 safetensors) · RTX A6000 · --place a 14.6 tok/sprefill 89.5 tok/s

MiniMax-M3.1-Flash

bloomery0.3.8 (75c7979e)nvfp4_rowsP5617 · G600 · cache 0%ctx 16koffload partialrtx-a6000linux1 stream! 1 caveat

midagedev

2026-10-24

bloomery · Raon-1 mini preview Q4_K_M + DFlash2 · RTX 3090 · 한국어 긴 답변 (전세·월세) 122 tok/sprefill 273 tok/s

raon-1-mini-preview-Q4_K_M.gguf

bloomery0.3.6 (e8bd14c0-dirty)q4_KP43 · G2048 · cache 0%ctx 256krtx-3090linux1 stream! 1 caveat

midagedev

2026-10-21

bloomery · Raon-1 mini preview Q4_K_M + DFlash2 · RTX 3090 · 한국어 (전세·월세) 124 tok/sprefill 276 tok/s

raon-1-mini-preview-Q4_K_M.gguf

bloomery0.3.6 (e8bd14c0-dirty)q4_KP23 · G387 · cache 0%ctx 256krtx-3090linux1 stream! 1 caveat

midagedev

2026-10-21

bloomery · MiniMax-M3 UD-IQ4_XS · RTX A6000 + host experts · 한국어 (전세·월세) 14.5 tok/sprefill 37.7 tok/s

MiniMax-M3-UD-IQ4_XS-00001-of-00006.gguf

bloomery0.3.6 (93c017bd-dirty)iq3_sP197 · G512 · cache 0%ctx 128koffload partialrtx-a6000linux1 stream

midagedev

2026-10-21

bloomery · Solar-Open2-250B · RTX 3090 · short chat 26.4 tok/sprefill 80.0 tok/s

solar-open2-250b

bloomery0.3.6 (a0288c5c0715)q4_KP30 · G400 · cache 0%ctx 8koffload partialrtx-3090 rtx-a6000linux1 stream! 3 caveats

midagedev

2026-10-20

bloomery · Solar-Open2-250B · RTX 3090 · 4.5K prompt 25.7 tok/sprefill 293 tok/s

solar-open2-250b

bloomery0.3.6 (a0288c5c0715)q4_KP4560 · G600 · cache 0%ctx 8koffload partialrtx-3090 rtx-a6000linux1 stream! 3 caveats

midagedev

2026-10-20

bloomery 0.3.4 (release head 9723698f2) · Nemotron 3.5 Bolt 74B-A9B · RTX A6000 · serving defaults, 5.7K-token prompt 87.4 tok/sprefill 2708 tok/s

NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB.gguf

bloomery0.3.4 (9723698f239b)iq2_xxsP5680 · G361 · cache 0%ctx 16krtx-3090 rtx-a6000linux1 stream! 1 caveat

midagedev

2026-10-17

bloomery 0.3.4 · Nemotron 3.5 Bolt 74B-A9B · RTX 3090 alone · 5.7K-token prompt 86.3 tok/sprefill 1981 tok/s

NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB.gguf

bloomery0.3.4 (85dd39c2f7f1)iq2_xxsP5680 · G361 · cache 0%ctx 16krtx-3090 rtx-a6000linux1 stream

midagedev

2026-10-17

bloomery 0.3.4 · Nemotron 3.5 Bolt 74B-A9B · RTX A6000 alone · 5.7K-token prompt 87.2 tok/sprefill 2692 tok/s

NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB.gguf

bloomery0.3.4 (85dd39c2f7f1)iq2_xxsP5680 · G361 · cache 0%ctx 16krtx-3090 rtx-a6000linux1 stream

midagedev

2026-10-17

NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB.gguf 87.5 tok/sprefill 2716 tok/s

bloomery0.3.4 (85dd39c2f7f1)iq2_xxsP5680 · G361 · cache 0%ctx 16krtx-3090 rtx-a6000linux1 stream

midagedev

2026-10-17

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

midagedev

2026-10-15

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

midagedev

2026-10-15

minicpm-v-4-7-35b-a3b 59.2 tok/s

bloomery0.3.2 (9bd7d5774c18)Q4_K_MP33 · G400 · cache 0%ctx 16krtx-3060linux1 stream! 1 caveat

midagedev

2026-10-14

minicpm-v-4-7-35b-a3b 59.6 tok/sprefill 605 tok/s

bloomery0.3.2 (9bd7d5774c18)Q4_K_MP5673 · G517 · cache 0%ctx 16krtx-3060linux1 stream

midagedev

2026-10-14

minicpm-v-4-7-35b-a3b 198 tok/sprefill 5530 tok/s

bloomery0.3.2 (9bd7d5774c18)P442 · G4096 · cache 0%ctx 16krtx-3090 rtx-a6000linux1 stream

anonymous

2026-10-13