DeepSeek-V4.1-Flash-Q3_K_M-00001-of-00009.gguf
bloomery0.2.1 (b83f1269)q3_KP26 · G400 · cache 0%ctx 32koffload partialrtx-a6000linux1 stream! 1 caveat
2026-10-05
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
128 runs, newest first · showing the first 30
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
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
bloomery0.1.0 (07ec8f04)q4_KP42 · G821 · cache 0%ctx 4koffload partialrtx-3090linux1 stream! 3 caveats
2026-10-02
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
bloomery0.1.0 (07ec8f04)q4_KP33 · G502 · cache 0%ctx 4koffload partialrtx-3090linux1 stream! 2 caveats
2026-10-02
bloomery · GLM-5.3-Flash UD-Q4_K_XL · RTX 3090 alone · coding review 497 in / 2000 out · residency + NextN MTP draft
26.2 tok/sprefill 176 tok/s
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
2026-10-02
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
bloomery0.1.0 (07ec8f04)q4_KP42 · G705 · cache 0%ctx 4koffload partialrtx-a6000linux1 stream! 3 caveats
2026-10-02
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
bloomery0.1.0 (07ec8f04)q4_KP33 · G524 · cache 0%ctx 4koffload partialrtx-a6000linux1 stream! 2 caveats
2026-10-02
bloomery · GLM-5.3-Flash UD-Q4_K_XL · A6000 alone · coding review 497 in / 2000 out · residency + NextN MTP draft
31.6 tok/sprefill 195 tok/s
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
bloomery0.1.0 (07ec8f04)q4_KP497 · G2000 · cache 0%ctx 4koffload partialrtx-a6000linux1 stream! 1 caveat
2026-10-02
clef-flash Q4_K_M on bloomery · Korean suite
93.6 ms p50engine 89.0 ms
clef-flash-Q4_K_M.gguf
2026-10-02
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
llama-serverb11036UD-Q4_K_XL321B · 23B activeP42 · G870 · cache 0%ctx 4kfa offoffload partialrtx-3090linux1 stream! 4 caveats
2026-10-02
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
llama-serverb11036UD-Q4_K_XL321B · 23B activeP33 · G522 · cache 0%ctx 4kfa offoffload partialrtx-3090linux1 stream! 3 caveats
2026-10-02
llama.cpp · GLM-5.3-Flash UD-Q4_K_XL · RTX 3090 alone · coding review 497 in / 2000 out · PR #27754 MTP draft, -ncmoe 43
20.3 tok/sprefill 93.1 tok/s
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
llama-serverb11036UD-Q4_K_XL321B · 23B activeP497 · G2000 · cache 0%ctx 4kfa offoffload partialrtx-3090linux1 stream! 2 caveats
2026-10-02
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
llama-serverb11036UD-Q4_K_XL321B · 23B activeP42 · G674 · cache 0%ctx 4kfa offoffload partialrtx-a6000linux1 stream! 4 caveats
2026-10-02
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
llama-serverb11036UD-Q4_K_XL321B · 23B activeP33 · G562 · cache 0%ctx 4kfa offoffload partialrtx-a6000linux1 stream! 3 caveats
2026-10-02
llama.cpp · GLM-5.3-Flash UD-Q4_K_XL · A6000 alone · coding review 497 in / 2000 out · PR #27754 MTP draft, -ncmoe 38
20.8 tok/sprefill 104 tok/s
GLM-5.3-Flash-UD-Q4_K_XL-00001-of-00006.gguf
llama-serverb11036UD-Q4_K_XL321B · 23B activeP497 · G2000 · cache 0%ctx 4kfa offoffload partialrtx-a6000linux1 stream! 1 caveat
2026-10-02
llama.cpp · Qwen3.8 Flash Next UD-Q4_K_XL · RTX 3090 alone · coding review 538 in / 1500 out · -ncmoe 43, no draft
35.5 tok/sprefill 73.1 tok/s
Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf
llama-serverb11157UD-Q4_K_XL177B · 10B activeP538 · G1500 · cache 0%ctx 8kfa onoffload partialrtx-3090linux1 stream! 3 caveats
2026-10-01
bloomery · Qwen3.8 Flash Next UD-Q4_K_XL · RTX 3090 alone · coding review 538 in / 1500 out · residency + MTP draft
71.1 tok/sprefill 389 tok/s
Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf
bloomery0.1.0 (b7e9f46b-dirty)q4_KP538 · G1500 · cache 0%ctx 8koffload partialrtx-3090linux1 stream! 1 caveat
2026-10-01
bloomery · Qwen3.8 Flash Next UD-Q4_K_XL · A6000 alone · coding review 538 in / 1500 out · residency + MTP draft
86.4 tok/sprefill 574 tok/s
Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf
bloomery0.1.0 (b7e9f46b-dirty)q4_KP538 · G1500 · cache 0%ctx 8koffload partialrtx-a6000linux1 stream! 1 caveat
2026-10-01
llama.cpp · Qwen3.8 Flash Next UD-Q4_K_XL · A6000 + 3090 · coding review 538 in / 1500 out · -ncmoe 21, no draft
44.3 tok/sprefill 217 tok/s
Qwen3.8-Flash-Next-UD-Q4_K_XL-00001-of-00004.gguf
llama-serverb11157UD-Q4_K_XL177B · 10B activeP538 · G1500 · cache 0%ctx 8kfa onoffload partialrtx-3090rtx-a6000linux1 stream! 2 caveats
2026-10-01
bloomery · V4.1 Flash Q3_K_M · 3090 + A6000 · coding review 507 in / 1500 out · residency + host streaming + DSpark
45.9 tok/sprefill 170 tok/s
DeepSeek-V4.1-Flash-Q3_K_M-00001-of-00009.gguf
bloomery0.1.0 (493ec88a)q3_KP507 · G1500 · cache 0%ctx 16koffload partialrtx-3090rtx-a6000linux1 stream
2026-09-30
ik_llama.cpp · V4.1 Flash Q3_K_M · 3090 + A6000 · coding review 507 in / 1500 out · DSpark n_max=3
28.8 tok/sprefill 156 tok/s
DeepSeek-V4.1-Flash-Q3_K_M-00001-of-00009.gguf
ik_llama.cpp81af2772Q3_K_M748B · 16B activeP507 · G1500 · cache 0%ctx 16koffload partialrtx-3090rtx-a6000linux1 stream! 2 caveats
2026-09-30
DeepSeek-V4.1-Flash-Q3_K_M-00001-of-00009.gguf
bloomery0.1.0 (a692575e)q3_KP29 · G400 · cache 0%ctx 16koffload partialrtx-3090rtx-a6000linux1 stream! 1 caveat
2026-09-29
DeepSeek-V4.1-Flash-Q3_K_M-00001-of-00009.gguf
bloomery0.1.0 (a692575e)q3_KP26 · G400 · cache 0%ctx 16koffload partialrtx-3090rtx-a6000linux1 stream! 2 caveats
2026-09-29
MiMo-V2.6-Flash-RL-MXFP4-00001-of-00002.gguf
31.1 tok/sprefill 266 tok/s
llama-serverb0MXFP4309B · 20B activeP765 · G843 · cache 0%ctx 32kfa onoffload partialrtx-3090rtx-a6000linux2 streams! 3 caveats
anonymous
2026-09-22
MiMo-V2.6-Flash-RL-MXFP4-00001-of-00002.gguf
24.0 tok/sprefill 293 tok/s
llama-serverb0MXFP4309B · 20B activeP6288 · G1646 · cache 0%ctx 32kfa onoffload partialrtx-3090rtx-a6000linux1 stream! 3 caveats
anonymous
2026-09-22
Ollama on an M1 Pro — llama3.2:1b
86.6 tok/s
llama3.2:1b
2026-09-21
llama3.2:1b
183 tok/s
anonymous
2026-09-20
Page views are counted with Cloudflare Web Analytics: no cookies, no fingerprinting. The toktape binary itself sends nothing anywhere.
