Drilldown: Recipe

DeepSeek V4.1 Flash on 4x 8 GB (GNmac) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Deepinfer-SM80 TP4 x PP2) (1) · Qwen3.8 Flash Next on 1x 8 GB (iIIusi0n SSD PLE) (1)

DeepSeek-V4.1-Flash-1017 (2) · 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 (mostly 3 bpw, 2 bpw on layers 18-22) from LibertAI's 2.9 bpw pack; attention, shared experts, indexer and DSpark drafter official FP8; KV fp8_ds_mla (1) · Official checkpoint (FP8 dense, FP4 experts); software FP8 on sm_80 (1)

vLLM a5a30471 plus a 13-file downstream patch (native Linux AIO PLE reader) (1) · vLLM PR #56201 head (79a7108d) plus the two Deepinfer-SM80 patches and 30 drop-in modules (1) · vLLM with a pinned sm_80 patch stack (built locally from source) (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 (3)

1 (1) · 4 (1) · 8 (1)

single card (1) · TP4 (default) or PP4 for x1/x4 links (1) · TP4 x PP2, partition 20,20 (1)

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

110.99 (1) · 153.35 (1) · 258 (1)

2,416 (1) · 2,636 (1) · 3,463 (1)

64 GiB, --gpu-memory-utilization 0.95 (1) · 64 GiB, --gpu-memory-utilization 0.96 (1) · 64 GiB, GPU_MEMORY_UTILIZATION 0.95 (1)

None (1) · 180 W (1) · 180 W (nvidia-smi -pl 180) (1)

None (1) · 610.43.03 (1) · CUDA 13 capable; measured on 610.43.02 (1)

None (1) · cmpunlocker (64 GiB) (1) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable driver for TP4 (1)

Proven (2) · Reported (1)

greencandle9753 (1) · HalfVulpes (1) · iIIusi0n (1)

September 19, 2026 (1) · October 26, 2026 (1) · October 28, 2026 (1)

https://github.com/GNmac-lab/deepseek-v41-flash-1017-cmp170hx (1) · https://github.com/HalfVulpes/Deepinfer-SM80 (1) · https://github.com/iIIusi0n/qwen3.8-flash-next-cmp170hx (1)