Drilldown: Recipe - CMP Wiki

Jump to content

Choose a table:

Recipe > page

: DeepSeek V4.1 Flash on 4x 8 GB (CurtisAccelerate TC-MoE)

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

& cards: 8 GB

Use the filters below to narrow your results.

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

Hybrid: LibertAI EXL3 2.9 bpw routed experts (layers 0-39), official FP8/FP4 for attention, shared experts, head, draft and Engram; KV fp8_ds_mla (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)

Morrowmake/vllm-cmp170hx (bind-mounted sm80 package) plus the author's tensor-core MoE kernels (1) · vLLM with a pinned sm_80 patch stack (built locally from source) (1)

recipe 1.2.0 (1) · vllm-cmp170hx 18305948ac; TC-MoE fb9786ec (1)

4 (2)

TP4 (default) or PP4 for x1/x4 links (1) · TP4, peer access off (NCCL_P2P_DISABLE=1), host all-reduce (1)

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

144.2 (1) · 258 (1)

1,523 (1) · 2,416 (1)

64 GiB, GPU_MEMORY_UTILIZATION 0.95 (1) · about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 (1)

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

None (1) · CUDA 13 capable; measured on 610.43.02 (1)

None (1) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable driver for TP4 (1)

Proven (1) · Reported (1)

CurtisAccelerate (1) · greencandle9753 (1)

October 22, 2026 (1) · October 26, 2026 (1)

https://github.com/CurtisAccelerate/DeepSeekv41-Flash-1017-EXL3-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 (CurtisAccelerate TC-MoE)

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

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