Drilldown: Recipe

DeepSeek V4.1 Flash on 4x 8 GB (Morrowmake) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Zanooda PP8) (1) · GLM 5.3 Flash on 4x 8 GB (1) · Qwen3.8 Flash Next on 1x 8 GB (iIIusi0n SSD PLE) (1)

DeepSeek-V4.1-Flash-1017 (2) · GLM-5.3-Flash (320B MoE, 18B active) (1) · Qwen3.8-Flash-Next (1)

AutoRound 3 bpw + MTP: klee100/Qwen3.8-Flash-Next-AutoRound-3bpw-MTP; 95.37 GiB BF16 PLE table on SSD (1) · Hybrid: routed experts EXL3 2.9 bpw (LibertAIDAI), everything else official FP8/BF16; KV BF16 (1) · Official checkpoint as downloaded: MXFP4 routed experts as Marlin W4A16, MXFP8 dense as Marlin W8A16; KV fp8 (1) · W4A16 (INT4 weights, group size 128, FP16 activations): canada-quant/GLM-5.3-Flash-W4A16-MTP (1)

Morrowmake/vllm-cmp170hx (vLLM fork, container image) (2) · vLLM a5a30471 plus a 13-file downstream patch (native Linux AIO PLE reader) (1) · vLLM PR #56201 head (79a7108d) plus a 20-patch sm_80 series; image zanooda/vllm-sm80-ds41f:v41-sm80 (1)

0.29.1rc1.dev402+ga5a30471f.ple1 (1) · recipe 1.0.0, engine a0c57b5237 (1) · recipe 1.8.0, engine 819146023f (1) · recipe 31318fd; patches 0001-0020 (1)

8 GB (4)

1 (1) · 4 (2) · 8 (1)

PP8, partition 5,5,5,5,5,5,5,5 (1) · single card (1) · TP4 (default) or PP4 (1) · TP4 with expert parallel (96 whole experts per card) (1)

1,048,576 (1) · 262,144 (2) · 262,144 advertised (tested through 32K) (1)

110.99 (1) · 117 (1) · 287 (1) · 442.1 (1)

2,636 (1) · 3,161 (1) · 3,818 (1) · 6,066 (1)

64 GB; weights 35.9 GB per rank (ranks 1-6), 37.6 GB rank 0, 46.3 GB rank 7 (1) · 64 GiB exposed, --gpu-memory-utilization 0.95 (2) · 64 GiB, --gpu-memory-utilization 0.96 (1)

180 W (3) · 180 W (one card unstable at 250 W) (1)

None (1) · 610.43.03 (1) · NVIDIA 580 or newer; P2P needs the Morrowmake/cmpunlocker build (2)

None · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable build · cmpunlocker (64 GiB, 74 SMs); Morrowmake/cmpunlocker for P2P · amoghmunikote/cmpunlocker 6c442eeb (patch 0016 SM reconfig, 74 SMs) plus Bayley P2P patches 0011/0013/0015 · cmpunlocker (64 GiB) · cmpunlocker (64 GiB); P2P-capable driver for the NCCL backend · cmpunlocker (64 GiB, 74 SMs) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable driver for TP4 · cmpunlocker fork with P2P (without Morrowmake's TRAP31 patch) · cmpunlocker v0.5+ (sudo ./install.sh --profile=8gb --no-iommu) · cmpunlocker with the BAR1 P2P patches (64 GiB BAR1 per card) · Morrowmake/cmpunlocker 1f2c498; modprobe RmForceEnableGen2=1, RMPcieLinkSpeed=0x1, ForceP2P=0x11 · Other

Proven (2) · Reported (2)

iIIusi0n (1) · voidgiraffe (2) · Zanooda (1)

September 19, 2026 (1) · October 16, 2026 (1) · October 19, 2026 (1) · October 24, 2026 (1)

https://github.com/iIIusi0n/qwen3.8-flash-next-cmp170hx (1) · https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe (1) · https://github.com/Morrowmake/glm53-flash-cmp170hx-recipe (1) · https://github.com/Zanooda/deepseek-v4.1-flash-cmp170hx (1)