Drilldown: Recipe

DeepSeek V4.1 Flash on 4x 8 GB (alanoo fidelity build) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Zanooda PP8) (1) · GLM 5.3 Flash on 2x 8 GB (ExLlamaV3 TP2) (1) · Qwen3.8 Flash Next on 4x 8 GB (1)

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

AWQ W4A16: wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16 (1) · EXL3 3.05 bpw: turboderp/GLM-5.3-Flash-exl3; DFlash2 drafter converted to EXL3 6 bpw (1) · Hybrid: all 40 expert layers at 3 bits (LibertAI 2.9 bpw pack with layers 18-22 grafted from the 3.5 bpw pack), official FP8 dense tensors (1) · Official checkpoint as downloaded: MXFP4 routed experts as Marlin W4A16, MXFP8 dense as Marlin W8A16; KV fp8 (1)

ExLlamaV3 (patched, pinned) (1) · GNmac-lab recipe image 1.2.0 (vLLM with sm_80 patches) plus three patches (1) · vLLM PR #56201 head (79a7108d) plus a 20-patch sm_80 series; image zanooda/vllm-sm80-ds41f:v41-sm80 (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 (4)

2 (1) · 4 (2) · 8 (1)

PP8, partition 5,5,5,5,5,5,5,5 (1) · TP2 over NCCL (GPU P2P), DFlash2 K7 plus hybrid drafting (1) · TP4 with expert parallel, MTP 3 (1) · TP4, P2P on (1)

1,000,000 (YaRN x4 from 262,144) (1) · 1,048,576 (1) · 262,144 (1) · 392,960 per request; 655,360-token Q8 KV pool shared by two requests (1)

105 (1) · 107.67 (1) · 116.49 (1) · 117 (1)

1,533 (1) · 2,101.4 (1) · 2,514 (1) · 6,066 (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 (64,911 MiB usable), GPU_MEMORY_UTILIZATION 0.98 (1) · about 62.9 / 62.3 GiB idle, peaks about 64.4 / 63.0 GiB with vision (1)

None (1) · 180 W (author's cards); about 170 W with a modest memory OC in his Discord numbers (1) · 180 W (one card unstable at 250 W) (1) · 200 W (1)

None (2) · 610.57.04 (1) · NVIDIA open 610.43.02 from a cmpunlocker fork with a P2P patch (1)

None (1) · cmpunlocker (64 GiB); P2P-capable driver for the NCCL backend (1) · cmpunlocker fork with P2P (without Morrowmake's TRAP31 patch) (1) · cmpunlocker with the BAR1 P2P patches (64 GiB BAR1 per card) (1)

Reported · Proven · Other · None

alanoo (1) · matstatman (1) · nestaa51 (1) · Zanooda (1)

October 13, 2026 (1) · October 16, 2026 (1) · October 19, 2026 (1) · October 27, 2026 (1)

https://discord.com/channels/1518634379604136178/1528826330454429706/1560602001908170753 (1) · https://github.com/alanoo81/deepseek-v41-flash-4x-cmp170hx (1) · https://github.com/alexvnesta/glm53-flash-cmp170hx-tp (1) · https://github.com/Zanooda/deepseek-v4.1-flash-cmp170hx (1)