Drilldown: Recipe - CMP Wiki

Jump to content

Choose a table:

Recipe > card count: 4-8

& decode tps: 20-110

Use the filters below to narrow your results.

DeepSeek V4.1 Flash on 4x 8 GB (alanoo fidelity build) (1) · 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) · GLM 5.3 on 8x 8 GB (Int4-Int8Mix PP8) (1) · GLM 5.3 on 8x 8 GB (vllm-170hx-glm5) (1)

DeepSeek-V4.1-Flash-1017 (3) · GLM-5.3 (full 78-layer DSA MoE, not Flash) (1) · GLM-5.3 (full 78-layer, not Flash) (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) · GLM-5.3-Int4-Int8Mix (INT4 / INT8 mix); KV fp8_ds_mla (1) · GLM-5.3-Int4-Int8Mix-AWQ-g64; drafter incoai/GLM-5.3-DFlash2 (1) · Hybrid: all 40 expert layers at 3 bits (LibertAI 2.9 bpw pack with layers 18-22 grafted from the 3.5 bpw pack), official FP8 dense tensors (1) · Official checkpoint: dense MXFP8 through an SM80 Marlin W8A16 path, routed experts MXFP4 through W4A16; KV FP8 (1)

Custom SM80 vLLM (patched from public commit 79a7108d9) (1) · ExLlamaV3 fork (anoane/exllamav3-anemone) + TabbyAPI fork (anoane/tabbyAPI) (1) · GNmac-lab recipe image 1.2.0 (vLLM with sm_80 patches) plus three patches (1) · Morrowmake/vllm-cmp170hx branch ampere-glm53 plus fail-closed source patches (1) · vLLM (build not stated) (1)

None (1) · GNmac-lab at 2ad5741ab1; image ds41-cmp170hx:1.2.0-fidelity (1) · reports 0.0.0; patches/public-base-to-runtime.patch (109 files) (1) · tag recipe-09 (309ef6d1); TabbyAPI deepseek-v41 (ce250ff) (1) · vLLM 0.30.1rc1, fork commit 378c37b0 (1)

8 GB (5)

4 (2) · 6 (1) · 8 (2)

PP8 (also PP9 and PP10), TP1 (1) · PP8, TP1 (1) · TP4, P2P on (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 (2) · 1,048,576 FP16 (1) · 1,048,576 per request (1) · 262,144 (1)

25 (1) · 48.7 (1) · 78.55 (1) · 99.9 (1) · 105 (1)

None (2) · 1,833 (1) · 2,116 (1) · 2,514 (1)

64 GB, --gpu-memory-utilization 0.95 (1) · 64 GiB (64,911 MiB usable), GPU_MEMORY_UTILIZATION 0.98 (1) · 64 GiB, --gpu-memory-utilization 0.97 (1) · 64 GiB, GPU_UTIL 0.96 at PP8 (1) · gpu_split 58 GB per CMP, 70 GB on the PRO (1)

None (1) · 150 W per CMP (PRO 400 W) (1) · 170 W (author's 10-card run) (1) · 200 W (2)

None (3) · NVIDIA open 610.43.02 from a cmpunlocker fork with a P2P patch (1) · NVIDIA open 610.57.04 patched with Morrowmake/cmpunlocker 1f2c498 (profile 8gb) (1)

None (3) · cmpunlocker fork with P2P (without Morrowmake's TRAP31 patch) (1) · Morrowmake/cmpunlocker 1f2c498; modprobe RmForceEnableGen2=1, RMPcieLinkSpeed=0x1, ForceP2P=0x11 (1)

Proven (1) · Reported (4)

1a2b3c0967 (1) · alanoo (1) · anoane (1) · reala7096 (1) · wgkbfcp (1)

September 29, 2026 (1) · October 7, 2026 (1) · October 19, 2026 (1) · October 20, 2026 (1) · October 27, 2026 (1)

https://discord.com/channels/1518634379604136178/1528826330454429706/1557523316120748073 (1) · https://github.com/alanoo81/deepseek-v41-flash-4x-cmp170hx (1) · https://github.com/anoane/09-deepseek-v41-flash-1017-exl3-tp5-1m (1) · https://github.com/arvkmr/vllm-170hx-glm5 (1) · https://github.com/wgkbfcp/deepseek-v4.1-flash-1017-cmp170hx-recipe (1)

Showing below up to 5 results in range #1 to #5.

D

DeepSeek V4.1 Flash on 6x 8 GB (TP6)

G

GLM 5.3 on 8x 8 GB (Int4-Int8Mix PP8)

GLM 5.3 on 8x 8 GB (vllm-170hx-glm5)

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