Drilldown: Recipe - CMP Wiki

Jump to content

Choose a table:

Recipe > page

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

or Qwen3.8 Flash Next on 1x 8 GB (ElectroHobo 3 bpw)

& cards: 8 GB

Use the filters below to narrow your results.

DeepSeek-V4.1-Flash-1017 (1) · Qwen3.8-Flash-Next (125B MoE per the recipe) (1)

AutoRound mixed 2/3-bit (klee100, 2.998 effective bpw, 47 GiB on card) plus halt95's FP8 n-gram table in host RAM (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 image with patch files mounted read-only (1) · vLLM with a pinned sm_80 patch stack (built locally from source) (1)

recipe 0.2.1; engine 18305948ac (1) · recipe 1.2.0 (1)

single card (1) · TP4 (default) or PP4 for x1/x4 links (1)

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

258 (1) · 296.4 (1)

2,416 (1) · 4,243 (1)

64 GiB, --gpu-memory-utilization 0.95 (fixed) (1) · 64 GiB, GPU_MEMORY_UTILIZATION 0.95 (1)

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

580 or newer (measured on 610.57.04) (1) · CUDA 13 capable; measured on 610.43.02 (1)

cmpunlocker (64 GiB, 74 SMs) (1) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable driver for TP4 (1)

Proven (1) · Reported (1)

greencandle9753 (1) · nathang6866 (1)

October 23, 2026 (1) · October 26, 2026 (1)

https://github.com/ElectroHobo/qwen38-flash-next-3bpw-1x-cmp170hx-recipe (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 (GNmac)

Q

Qwen3.8 Flash Next on 1x 8 GB (ElectroHobo 3 bpw)

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