Drilldown: Recipe

DeepSeek V4.1 Flash on 4x 8 GB (alanoo fidelity build) (1) · GLM 5.3 on 8x 8 GB (Int4-Int8Mix PP8) (1) · Qwen3.8 Flash Next on 2x 8 GB (DUFRelic PP2) (1)

DeepSeek-V4.1-Flash-1017 (1) · GLM-5.3 (full 78-layer, not Flash) (1) · Qwen3.8-Flash-Next (1)

GLM-5.3-Int4-Int8Mix (INT4 / INT8 mix); KV fp8_ds_mla (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) · W4A16 INT4 g128 with the PLE table repacked INT4 g32: zankich/Qwen3.8-Flash-Next-W4A16-Merlin-INT4PLE-FP8KV; KV BF16 (1)

GNmac-lab recipe image 1.2.0 (vLLM with sm_80 patches) plus three patches (1) · vLLM (build not stated) (1) · vLLM v0.30.0 + zankich INT4-PLE plugin + six hash-guarded patch layers (1)

None (1) · GNmac-lab at 2ad5741ab1; image ds41-cmp170hx:1.2.0-fidelity (1) · vLLM v0.30.0 (ced6857a); plugin zankich/vllm v0.29.0z (6609bfef) (1)

8 GB · Other · None

2 (1) · 4 (1) · 8 (1)

PP2, MTP depth 3 (1) · PP8, TP1 (1) · TP4, P2P on (1)

1,048,576 (1) · 262,144 (2)

25 (1) · 105 (1) · 133.39 (1)

None (1) · 2,514 (1) · 6,213.66 (1)

64 GiB (64,911 MiB usable), GPU_MEMORY_UTILIZATION 0.98 (1) · 64 GiB, --gpu-memory-utilization 0.90 (1) · 64 GiB, --gpu-memory-utilization 0.97 (1)

None · 180 W · 200 W · 140 W · 140 W (200 W observed-draw abort guard) · 150 W per CMP (PRO 400 W) · 170 W (author's 10-card run) · 180 W (author's cards); about 170 W with a modest memory OC in his Discord numbers · 180 W (nvidia-smi -pl 180) · 180 W (one card unstable at 250 W) · Other

None (1) · NVIDIA 610.43.02 (1) · NVIDIA open 610.43.02 from a cmpunlocker fork with a P2P patch (1)

None (1) · amoghmunikote/cmpunlocker 6c442eeb (patch 0016 SM reconfig, 74 SMs) plus Bayley P2P patches 0011/0013/0015 (1) · cmpunlocker fork with P2P (without Morrowmake's TRAP31 patch) (1)

Reported (3)

1a2b3c0967 (1) · alanoo (1) · dufrelic (1)

October 3, 2026 (1) · October 7, 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/DUFRelic/qwen38-flash-next-recipe (1)