Drilldown: Recipe

DeepSeek V4.1 Flash heretic on 4x 8 GB (1) · DeepSeek V4.1 Flash on 6x 8 GB (Deepinfer-SM80 TP2 x PP3) (1) · DeepSeek V4.1 Flash on 6x 8 GB (TP6) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Deepinfer-SM80 TP4 x PP2) (1) · GLM 5.3 Flash on 3x 8 GB (1) · Qwen3.8 Flash Next on 3x 8 GB (clee PP3) (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) · GLM-5.3-Flash (320B MoE, 18B active) (1) · Qwen3.8-Flash-Next (2)

AWQ W4A16: wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16 (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 (2) · Official checkpoint: dense MXFP8 through an SM80 Marlin W8A16 path, routed experts MXFP4 through W4A16; KV FP8 (1) · W4A16 AutoRound: Intel/Qwen3.8-Flash-Next-W4A16-AutoRound; 95.4 GiB BF16 PLE table streamed from NVMe; KV fp8 e4m3 (software-decoded on SM80) (1) · W4A16, about 4.3 bpw, 163 GiB on disk (1)

Custom SM80 vLLM (patched from public commit 79a7108d9) (1) · Morrowmake/vllm-cmp170hx (via the glm53-flash-cmp170hx-recipe) (1) · Morrowmake/vllm-cmp170hx (vLLM fork, container image) (1) · vLLM nightly 7d0b4e57 plus the author's pure-Python fork clee/vllm-sm80 (branch q38fn/stack) (1) · vLLM PR #56201 head (79a7108d) plus the two Deepinfer-SM80 patches and 30 drop-in modules (2) · wtdcode/vllm-backport (image lazymio/vllm-backport:latest-sm80) (1)

Deepinfer-SM80 2a828fc lineage; vLLM v0.28.1rc0 base (1) · Deepinfer-SM80, vLLM v0.28.1rc0 base (1) · latest-sm80 tag as of 2026-10-16 (1) · not stated (1) · q38fn/stack on nightly-7d0b4e57 (1) · recipe 1.0.0 (commit d4d1f525), engine a0c57b52 (1) · reports 0.0.0; patches/public-base-to-runtime.patch (109 files) (1)

8 GB (7)

3 (2) · 4 (2) · 6 (2) · 8 (1)

PP3 (1) · PP3, no P2P (works at PP2 on two cards) (1) · TP2 x PP3, partition 14,14,12 (1) · TP4 (1) · TP4 with expert parallel, MTP 3 (1) · TP4 x PP2, partition 20,20 (1) · TP6 (virtual-head padding), PP1 (1)

1,000,000 (YaRN x4 from 262,144) (1) · 1,048,576 (3) · 1,048,576 (YaRN x4) (1) · 262,144 (1) · about 1,000,000 (8-bit KV cache) (1)

None (1) · 70 - 170 (6)

None (2) · 2,101.4 (1) · 2,453 (1) · 3,463 (1) · 4,037 (1) · 4,831 (1)

64 GB (1) · 64 GB, --gpu-memory-utilization 0.95 (1) · 64 GiB (2) · 64 GiB, --gpu-memory-utilization 0.92 (miner co-resident) (1) · 64 GiB, --gpu-memory-utilization 0.95 (1) · 64 GiB, gpu-memory-utilization 0.92 (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 (7)

None (7)

Proven (1) · Reported (6)

c133 (1) · darkmaniac7 (1) · HalfVulpes (2) · matstatman (1) · shirogeek (1) · wgkbfcp (1)

October 10, 2026 (1) · October 16, 2026 (1) · October 19, 2026 (2) · October 28, 2026 (2) · October 29, 2026 (1)

https://discord.com/channels/1518634379604136178/1518695289278566450/1561743826945843304 (1) · https://discord.com/channels/1518634379604136178/1528826330454429706/1560602001908170753 (1) · https://github.com/clee/qwen3.8-flash-next-3x170hx (1) · https://github.com/HalfVulpes/Deepinfer-SM80 (2) · https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe (1) · https://github.com/wgkbfcp/deepseek-v4.1-flash-1017-cmp170hx-recipe (1)