toktapethe record, not a recording of it

midagedev

https://github.com/midagedev

52 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-3090rtx-a6000linux1 stream! 2 caveats

midagedev

2026-11-03

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-3090rtx-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-3090rtx-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-3090rtx-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 · 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-3090rtx-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-3090rtx-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-3090rtx-a6000linux1 stream! 1 caveat

midagedev

2026-10-17

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-3090rtx-a6000linux1 stream! 2 caveats

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-3090rtx-a6000linux1 stream

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-3090rtx-a6000linux1 stream! 2 caveats

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-3090rtx-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-3090rtx-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

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-3090rtx-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-3090rtx-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-3090rtx-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-3090rtx-a6000linux1 stream

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-3090rtx-a6000linux1 stream

midagedev

2026-10-07

One RTX 3090 · Strata 6f32ec0 · Qwen3.8 Flash Next UD-Q4_K_XL 111 GB (same file) · code review, 1500 tokens 51.7 tok/sprefill 265 tok/s

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

llama-serverStrata 0.1.39UD-Q4_K_XL177B · 10B activeP538 · G1500 · cache 0%ctx 32krtx-3090linux1 stream! 4 caveats

midagedev

2026-10-06

One RTX 3090 · Strata 6f32ec0 · Qwen3.8 Flash Next UD-Q4_K_XL 111 GB (same file) · Korean chat 43.8 tok/s

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

llama-serverStrata 0.1.39UD-Q4_K_XL177B · 10B activeP33 · G400 · cache 0%ctx 32krtx-3090linux1 stream! 5 caveats

midagedev

2026-10-06

One RTX 3090 · Strata 6f32ec0 · Qwen3.8 Flash Next UD-Q4_K_XL 111 GB (same file) · Rust chat 46.1 tok/s

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

llama-serverStrata 0.1.39UD-Q4_K_XL177B · 10B activeP33 · G400 · cache 0%ctx 32krtx-3090linux1 stream! 5 caveats

midagedev

2026-10-06

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

midagedev

2026-10-06

One RTX 3090 · Strata 6f32ec0 · Qwen3.8 Flash Next IQ3_XXS 76 GB · Korean chat 91.4 tok/s

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

midagedev

2026-10-06

One RTX 3090 · Strata 6f32ec0 · Qwen3.8 Flash Next IQ3_XXS 76 GB · Rust chat 99.7 tok/s

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

midagedev

2026-10-06

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

One RTX 3090 · bloomery 0.2.1 · Qwen3.8 Flash Next UD-Q4_K_XL 111 GB · Rust chat 66.5 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! 1 caveat

midagedev

2026-10-06

Older runs →

Page views are counted with Cloudflare Web Analytics: no cookies, no fingerprinting. The toktape binary itself sends nothing anywhere.