Drilldown: Recipe - CMP Wiki

Jump to content

Choose a table:

Recipe > decode tps: 70-100

Use the filters below to narrow your results.

DeepSeek V4.1 Flash on 4x 8 GB plus RTX PRO 6000 (ExLlamaV3 TP5) (1) · DeepSeek V4.1 Flash on 6x 8 GB (TP6) (1) · Qwen3.8 Flash Next on 2x 8 GB (vektorprime PP2) (1) · Qwen3.8 Flash Next on 3x 8 GB (clee PP3) (1)

DeepSeek-V4.1-Flash-1017 (2) · Qwen3.8-Flash-Next (2)

AWQ INT4: cyankiwi/Qwen3.8-Flash-Next-AWQ-INT4; 95 GiB BF16 PLE table in host RAM (FP8 table optional) (1) · EXL3 3.5 bpw (LibertAIDAI; routed experts 4 bpw on layers 0-9 and 30-39, 3 bpw on 10-29; attention and shared experts 6 bpw) plus the official Engram shards (1) · Official checkpoint: dense MXFP8 through an SM80 Marlin W8A16 path, routed experts MXFP4 through W4A16; KV FP8 (1) · W4A16 AutoRound: Intel/Qwen3.8-Flash-Next-W4A16-AutoRound; 95.4 GiB BF16 PLE table streamed from NVMe; KV fp8 e4m3 (software-decoded on SM80) (1)

Custom SM80 vLLM (patched from public commit 79a7108d9) (1) · ExLlamaV3 fork (anoane/exllamav3-anemone) + TabbyAPI fork (anoane/tabbyAPI) (1) · vLLM nightly + PR #53899 (a5530b9) + the repo's patch scripts (1) · vLLM nightly 7d0b4e57 plus the author's pure-Python fork clee/vllm-sm80 (branch q38fn/stack) (1)

0.1.dev1+ga5530b90c.d20260829 (1) · q38fn/stack on nightly-7d0b4e57 (1) · reports 0.0.0; patches/public-base-to-runtime.patch (109 files) (1) · tag recipe-09 (309ef6d1); TabbyAPI deepseek-v41 (ce250ff) (1)

8 GB (4)

2 (1) · 3 (1) · 4 (1) · 6 (1)

PP2 with PLE CPU offload (1) · PP3, no P2P (works at PP2 on two cards) (1) · TP5 across four CMP 170HX and one RTX PRO 6000 Blackwell (native backend, reduces through host memory); MTP draft on the PRO (1) · TP6 (virtual-head padding), PP1 (1)

1,048,576 (1) · 1,048,576 (YaRN x4) (1) · 1,048,576 FP16 (1) · 262,144 (1)

74.4 (1) · 75.4 (1) · 78.55 (1) · 99.9 (1)

None (2) · 2,116 (1) · 4,831 (1)

64 GB, --gpu-memory-utilization 0.95 (1) · 64 GiB, gpu-memory-utilization 0.92 (1) · 64 GiB; weights PP0 39.48 GiB, PP1 45.53 GiB; --gpu-memory-utilization 0.9 (1) · gpu_split 58 GB per CMP, 70 GB on the PRO (1)

None (3) · 150 W per CMP (PRO 400 W) (1)

None (3) · NVIDIA open 610.57.04 patched with Morrowmake/cmpunlocker 1f2c498 (profile 8gb) (1)

None (3) · Morrowmake/cmpunlocker 1f2c498; modprobe RmForceEnableGen2=1, RMPcieLinkSpeed=0x1, ForceP2P=0x11 (1)

Proven (1) · Reported (3)

anoane (1) · c133 (1) · vektor_prime (1) · wgkbfcp (1)

August 2026 (1) · October 2026 (3)

https://github.com/anoane/09-deepseek-v41-flash-1017-exl3-tp5-1m (1) · https://github.com/clee/qwen3.8-flash-next-3x170hx (1) · https://github.com/vektorprime/qwen38-flash-next-pp2 (1) · https://github.com/wgkbfcp/deepseek-v4.1-flash-1017-cmp170hx-recipe (1)

Showing below up to 4 results in range #1 to #4.

Retrieved from "https://cmp.wiki/wiki/Special:Drilldown/Recipe"