Drilldown: Recipe

DeepSeek V4.1 Flash on 4x 8 GB (CurtisAccelerate TC-MoE) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Zanooda PP8) (1) · Qwen3.8 Flash Next on 1x 8 GB (iIIusi0n SSD PLE) (1) · Qwen3.8 Flash Next on 2x 8 GB (DUFRelic PP2) (1) · Qwen3.8 Flash Next on 4x 8 GB (1)

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

AutoRound 3 bpw + MTP: klee100/Qwen3.8-Flash-Next-AutoRound-3bpw-MTP; 95.37 GiB BF16 PLE table on SSD (1) · AWQ W4A16: wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16 (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) · Official checkpoint as downloaded: MXFP4 routed experts as Marlin W4A16, MXFP8 dense as Marlin W8A16; KV fp8 (1) · W4A16 INT4 g128 with the PLE table repacked INT4 g32: zankich/Qwen3.8-Flash-Next-W4A16-Merlin-INT4PLE-FP8KV; KV BF16 (1)

Morrowmake/vllm-cmp170hx (bind-mounted sm80 package) plus the author's tensor-core MoE kernels (1) · 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) · vLLM v0.30.0 + zankich INT4-PLE plugin + six hash-guarded patch layers (1) · wtdcode/vllm-backport (image lazymio/vllm-backport:latest-sm80) (1)

None · recipe 0.2.1; engine 18305948ac · 0.1.dev1+ga5530b90c.d20260829 · 0.29.1rc1.dev402+ga5a30471f.ple1 · Deepinfer-SM80 2a828fc lineage; vLLM v0.28.1rc0 base · Deepinfer-SM80, vLLM v0.28.1rc0 base · Flun/glm53-flash-cmp170hx-exl3 at 5933112 · GNmac-lab at 2ad5741ab1; image ds41-cmp170hx:1.2.0-fidelity · latest-sm80 tag as of 2026-10-16 · not stated · q38fn/stack on nightly-7d0b4e57 · recipe 0.3.1; engine 18305948ac · recipe 1.0.0 (commit d4d1f525), engine a0c57b52 · recipe 1.0.0, engine a0c57b5237 · recipe 1.2.0 · recipe 1.8.0, engine 819146023f · recipe 31318fd; patches 0001-0020 · reports 0.0.0; patches/public-base-to-runtime.patch (109 files) · tag qwen38-recipe-1.0.0, engine 18305948ac · tag recipe-09 (309ef6d1); TabbyAPI deepseek-v41 (ce250ff) · upstream dev 0f685aa9fd plus 9 patches; repo db01c256 · v1.0.6 (this row) · vLLM 0.30.1rc1, fork commit 378c37b0 · vLLM v0.30.0 (ced6857a); plugin zankich/vllm v0.29.0z (6609bfef) · vllm-backport 3142ded1 · vllm-cmp170hx 18305948ac; TC-MoE fb9786ec · Other

8 GB (5)

1 (1) · 2 (1) · 4 (2) · 8 (1)

PP2, MTP depth 3 (1) · PP8, partition 5,5,5,5,5,5,5,5 (1) · single card (1) · TP4 with expert parallel, MTP 3 (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 (1) · 262,144 (1) · 262,144 (weights address 1,048,576) (1) · 262,144 advertised (tested through 32K) (1)

110.99 (1) · 116.49 (1) · 117 (1) · 133.39 (1) · 144.2 (1)

1,523 (1) · 2,101.4 (1) · 2,636 (1) · 6,066 (1) · 6,213.66 (1)

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 0.90 (1) · 64 GiB, --gpu-memory-utilization 0.96 (1) · about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 (1)

None (1) · 140 W (1) · 140 W (200 W observed-draw abort guard) (1) · 180 W (1) · 180 W (one card unstable at 250 W) (1)

None (3) · 610.43.03 (1) · NVIDIA 610.43.02 (1)

None (2) · amoghmunikote/cmpunlocker 6c442eeb (patch 0016 SM reconfig, 74 SMs) plus Bayley P2P patches 0011/0013/0015 (1) · cmpunlocker (64 GiB) (1) · cmpunlocker with the BAR1 P2P patches (64 GiB BAR1 per card) (1)

Proven (1) · Reported (4)

CurtisAccelerate (1) · dufrelic (1) · iIIusi0n (1) · matstatman (1) · Zanooda (1)

September 19, 2026 (1) · October 3, 2026 (1) · October 16, 2026 (1) · October 19, 2026 (1) · October 22, 2026 (1)

https://discord.com/channels/1518634379604136178/1528826330454429706/1560602001908170753 (1) · https://github.com/CurtisAccelerate/DeepSeekv41-Flash-1017-EXL3-CMP170HX (1) · https://github.com/DUFRelic/qwen38-flash-next-recipe (1) · https://github.com/iIIusi0n/qwen3.8-flash-next-cmp170hx (1) · https://github.com/Zanooda/deepseek-v4.1-flash-cmp170hx (1)