Drilldown: Recipe

DeepSeek V4.1 Flash heretic on 4x 8 GB (1) · DeepSeek V4.1 Flash on 4x 8 GB (CurtisAccelerate TC-MoE) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Deepinfer-SM80 TP4 x PP2) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Zanooda PP8) (1) · Qwen3.8 Flash Next on 2x 8 GB (Morrowmake EXL3) (1) · Qwen3.8 Flash Next on 4x 8 GB (1)

DeepSeek-V4.1-Flash-1017 (3) · DeepSeek-V4.1-Flash-1017 heretic (pqhaz abliteration) (1) · Qwen3.8-Flash-Next (2)

AWQ W4A16: wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16 (1) · EXL3 5.05 bpw; PLE (n-gram) table read from SSD (1) · 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 2.9 bpw (LibertAIDAI), everything else official FP8/BF16 with the 38 heretic attn.wo_b tensors (1) · Official checkpoint (FP8 dense, FP4 experts); software FP8 on sm_80 (1) · Official checkpoint as downloaded: MXFP4 routed experts as Marlin W4A16, MXFP8 dense as Marlin W8A16; KV fp8 (1)

Morrowmake/vllm-cmp170hx (bind-mounted sm80 package) plus the author's tensor-core MoE kernels (1) · Morrowmake/vllm-cmp170hx (EXL3 path) (1) · Morrowmake/vllm-cmp170hx (vLLM fork, container image) (1) · vLLM PR #56201 head (79a7108d) plus a 20-patch sm_80 series; image zanooda/vllm-sm80-ds41f:v41-sm80 (1) · vLLM PR #56201 head (79a7108d) plus the two Deepinfer-SM80 patches and 30 drop-in modules (1) · wtdcode/vllm-backport (image lazymio/vllm-backport:latest-sm80) (1)

Deepinfer-SM80, vLLM v0.28.1rc0 base (1) · latest-sm80 tag as of 2026-10-16 (1) · recipe 1.0.0 (commit d4d1f525), engine a0c57b52 (1) · recipe 31318fd; patches 0001-0020 (1) · tag qwen38-recipe-1.0.0, engine 18305948ac (1) · vllm-cmp170hx 18305948ac; TC-MoE fb9786ec (1)

8 GB (6)

2 (1) · 4 (3) · 8 (2)

PP8, partition 5,5,5,5,5,5,5,5 (1) · TP2 with expert parallel (1) · TP4 (1) · TP4 with expert parallel, MTP 3 (1) · TP4 x PP2, partition 20,20 (1) · TP4, peer access off (NCCL_P2P_DISABLE=1), host all-reduce (1)

1,000,000 (YaRN x4 from 262,144) (1) · 1,048,576 (2) · 262,144 (2) · 262,144 (weights address 1,048,576) (1)

110 - 160 (6)

1,000 - 7,000 (6)

64 GB (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, --gpu-memory-utilization 0.92 (miner co-resident) (1) · 64 GiB, --gpu-memory-utilization 0.95 (2) · about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 (1)

None (4) · 140 W (1) · 180 W (one card unstable at 250 W) (1)

None · 580 or newer (measured on 610.57.04) · NVIDIA 580 or newer; P2P needs the Morrowmake/cmpunlocker build · 580 or newer (measured on 610.57.04); open modules with HMM for the table-on-disk mode · 610.43.03 · 610.57.04 · CUDA 13 capable; measured on 610.43.02 · NVIDIA 610.43.02 · NVIDIA open 610.43.02 from a cmpunlocker fork with a P2P patch · NVIDIA open 610.57.04 patched with Morrowmake/cmpunlocker 1f2c498 (profile 8gb) · nvidia-open 610.43.02 + cmpunlocker v0.5 or newer · Other

None (5) · cmpunlocker with the BAR1 P2P patches (64 GiB BAR1 per card) (1)

Reported · Proven · Other · None

CurtisAccelerate (1) · darkmaniac7 (1) · HalfVulpes (1) · matstatman (1) · voidgiraffe (1) · Zanooda (1)

October 16, 2026 (2) · October 19, 2026 (1) · October 22, 2026 (1) · October 28, 2026 (1) · October 29, 2026 (1)

https://discord.com/channels/1518634379604136178/1528826330454429706/1560602001908170753 (1) · https://github.com/CurtisAccelerate/DeepSeekv41-Flash-1017-EXL3-CMP170HX (1) · https://github.com/HalfVulpes/Deepinfer-SM80 (1) · https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe (1) · https://github.com/Morrowmake/qwen38-flash-next-cmp170hx-recipe (1) · https://github.com/Zanooda/deepseek-v4.1-flash-cmp170hx (1)