Drilldown: Recipe - CMP Wiki

Jump to content

Choose a table:

Recipe > page

: DeepSeek V4.1 Flash on 4x 8 GB (GNmac)

or DeepSeek V4.1 Flash on 4x 8 GB (alanoo fidelity build)

& cards: 8 GB

Use the filters below to narrow your results.

DeepSeek-V4.1-Flash-1017 (2)

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) · Hybrid: routed experts EXL3 (mostly 3 bpw, 2 bpw on layers 18-22) from LibertAI's 2.9 bpw pack; attention, shared experts, indexer and DSpark drafter official FP8; KV fp8_ds_mla (1)

GNmac-lab recipe image 1.2.0 (vLLM with sm_80 patches) plus three patches (1) · vLLM with a pinned sm_80 patch stack (built locally from source) (1)

GNmac-lab at 2ad5741ab1; image ds41-cmp170hx:1.2.0-fidelity (1) · recipe 1.2.0 (1)

4 (2)

TP4 (default) or PP4 for x1/x4 links (1) · TP4, P2P on (1)

262,144 (1) · 262,144 (up to 1,048,576) (1)

105 (1) · 258 (1)

2,416 (1) · 2,514 (1)

64 GiB (64,911 MiB usable), GPU_MEMORY_UTILIZATION 0.98 (1) · 64 GiB, GPU_MEMORY_UTILIZATION 0.95 (1)

180 W (nvidia-smi -pl 180) (1) · 200 W (1)

CUDA 13 capable; measured on 610.43.02 (1) · NVIDIA open 610.43.02 from a cmpunlocker fork with a P2P patch (1)

cmpunlocker (64 GiB, 74 SMs) with a P2P-capable driver for TP4 (1) · cmpunlocker fork with P2P (without Morrowmake's TRAP31 patch) (1)

Proven (1) · Reported (1)

alanoo (1) · greencandle9753 (1)

October 26, 2026 (1) · October 27, 2026 (1)

https://github.com/alanoo81/deepseek-v41-flash-4x-cmp170hx (1) · https://github.com/GNmac-lab/deepseek-v41-flash-1017-cmp170hx (1)

Showing below up to 2 results in range #1 to #2.

D

DeepSeek V4.1 Flash on 4x 8 GB (alanoo fidelity build)

DeepSeek V4.1 Flash on 4x 8 GB (GNmac)

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