Drilldown: Recipe

DeepSeek V4.1 Flash on 2x 8 GB (Project Maya) (1) · DeepSeek V4.1 Flash on 6x 8 GB (TP6) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Zanooda PP8) (1) · GLM 5.3 Flash on 2x 8 GB (Project Maya) (1) · GLM 5.3 Flash on 8x 8 GB (promisezackr PP8 NVFP4 DFlash2) (1) · Qwen3.8 Flash Next on 2x 8 GB (vektorprime PP2) (1) · Qwen3.8 Flash Next on 3x or 4x 8 GB (zebgop-ops FP8 PP) (1) · Qwen3.8 Flash Next on 4x 8 GB (1)

DeepSeek-V4.1-Flash-1017 (2) · DeepSeek-V4.1-Flash-1017 (748B in the Maya README) (1) · GLM-5.3-Flash (1) · GLM-5.3-Flash (321B in the Maya README) (1) · Qwen/Qwen3.8-Flash-Next-FP8 (revision bcd9f01d) (1) · Qwen3.8-Flash-Next (2)

AWQ INT4: cyankiwi/Qwen3.8-Flash-Next-AWQ-INT4; 95 GiB BF16 PLE table in host RAM (FP8 table optional) (1) · AWQ W4A16: wtdcode/Qwen3.8-Flash-Next-AWQ-W4A16 (1) · LibertAIDAI/GLM-5.3-Flash-NVFP4 (ModelOpt NVFP4, routed experts only, 181 GiB), run through Marlin W4A16 kernels; GLM-5.3-Flash DFlash2 drafter (5 sliding-window layers) (1) · Maya GGUF (Maya-S 340 GB or Maya-XS 277 GB; Engram tables stay on SSD) (1) · Maya-M GGUF (116 GB), every expert in VRAM; Maya-S (96.5 GB) and Maya-S24 (94.7 GB) also reported (1) · Official block FP8, about 126 GiB including the about 50 GiB FP8 n-gram (PLE) table, which is served from host RAM; KV cache bf16 (the QSA layers refuse fp8) (1) · Official checkpoint as downloaded: MXFP4 routed experts as Marlin W4A16, MXFP8 dense as Marlin W8A16; KV fp8 (1) · Official checkpoint: dense MXFP8 through an SM80 Marlin W8A16 path, routed experts MXFP4 through W4A16; KV FP8 (1)

Custom SM80 vLLM (patched from public commit 79a7108d9) (1) · Project Maya (Strata and llama.cpp lineage) (1) · Project Maya (Strata and llama.cpp lineage, EXL3 loading, DFlash2 drafter) (1) · vLLM nightly + PR #53899 (a5530b9) + the repo's patch scripts (1) · vLLM PR #56201 head (79a7108d) plus a 20-patch sm_80 series; image zanooda/vllm-sm80-ds41f:v41-sm80 (1) · vLLM: official vllm/vllm-openai:glm53-flash image plus promisezackr's 24 patches (SM8x base from 344303947/vllm170hx, pipeline parallel for GLM-5.3-Flash, DFlash2 under PP8) (1) · vLLM: the vllm/vllm-openai:qwen38-flash-next image with zebgop-ops patches 0001 to 0016 (never 0008-WITHDRAWN) and three ported files (1) · wtdcode/vllm-backport (image lazymio/vllm-backport:latest-sm80) (1)

None (1) · 0.1.dev1+ga5530b90c.d20260829 (1) · 0.1.dev20073+g8e685d198; repo commit 2f551bb (patch 0016, 2026-10-02) (1) · latest-sm80 tag as of 2026-10-16 (1) · recipe 31318fd; patches 0001-0020 (1) · reports 0.0.0; patches/public-base-to-runtime.patch (109 files) (1) · v0.1.dev20051+g487ecf187 (the image's vLLM); repo commit 90ec72e (1) · v1.0.6 (this row) (1)

8 GB (8)

2 (3) · 4 (2) · 6 (1) · 8 (2)

engine-managed expert tiering across VRAM, host RAM and NVMe (1) · engine-managed split with expert tiering across VRAM, RAM and NVMe (1) · PP2 with PLE CPU offload (1) · PP4, VLLM_PP_LAYER_PARTITION=12,12,12,12, MTP 3, FULL_AND_PIECEWISE CUDA graphs; PCIe Gen2 x4 per card, no P2P. Three cards: PP3 with 16,17,15 or 16,16,16 (1) · PP8 (VLLM_PP_LAYER_PARTITION=7,5,7,5,7,5,7,2) with DFlash2, 7 draft tokens; PCIe Gen2 x4, no P2P; host 2x Xeon E5-2690 v4, 96 GB DDR4 (1) · PP8, partition 5,5,5,5,5,5,5,5 (1) · TP4 with expert parallel, MTP 3 (1) · TP6 (virtual-head padding), PP1 (1)

None (2) · 1,000,000 (YaRN x4 from 262,144) (1) · 1,048,576 (2) · 1,048,576 (KV pool 6.62M tokens at utilization 0.90, about 6.3 concurrent 1M requests) (1) · 262,144 (1) · 262,144 native; 524,288 with YaRN 2.0; 1,048,576 with YaRN 4.0 (needle verified on PP3) (1)

60 - 80 (4) · 80 - 130 (4)

None (4) · 514 (1) · 2,101.4 (1) · 6,066 (1) · 11,100 (1)

64 GB (3) · 64 GB, --gpu-memory-utilization 0.90 (1) · 64 GB, --gpu-memory-utilization 0.95 (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 0.94 plus per-rank KV budgets; measured 34.0-34.3 GiB per 12-layer rank, 37.9 GiB on the drafter rank (1) · 64 GiB; weights PP0 39.48 GiB, PP1 45.53 GiB; --gpu-memory-utilization 0.9 (1)

None (6) · 180 W (one card unstable at 250 W) (1) · 200 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 · 610.43.02 (nvidia-driver-610-open) · 610.43.03 · 610.43.03 (open modules) · 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 610.43.03, CUDA 13.0 · 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 VRAM unlock (64 GB per card) (1) · cmpunlocker VRAM unlock (64 GiB per card) (1) · cmpunlocker with the BAR1 P2P patches (64 GiB BAR1 per card) (1)

Reported · Proven · Other · None

flipnburner (1) · matstatman (1) · pcsv. (1) · promisezackr (1) · vektor_prime (1) · wgkbfcp (1) · ZackO2o (1) · Zanooda (1)

August 2026 (2) · September 2026 (1) · October 2026 (4)

https://discord.com/channels/1518634379604136178/1528826330454429706/1560602001908170753 (1) · https://github.com/mw00/project-maya#how-fast-is-it (2) · https://github.com/promisezackr/glm53-flash-170hx-pp8 (1) · https://github.com/vektorprime/qwen38-flash-next-pp2 (1) · https://github.com/wgkbfcp/deepseek-v4.1-flash-1017-cmp170hx-recipe (1) · https://github.com/Zanooda/deepseek-v4.1-flash-cmp170hx (1) · https://github.com/zebgop-ops/qwen38-flashnext-pp (1)