Drilldown: Recipe

DeepSeek V4.1 Flash on 2x 8 GB (Project Maya) (1) · DeepSeek V4.1 Flash on 4x 8 GB (Morrowmake) (1) · DeepSeek V4.1 Flash on 6x 8 GB (Deepinfer-SM80 TP2 x PP3) (1) · DeepSeek V4.1 Flash on 8x 8 GB (Deepinfer-SM80 TP4 x PP2) (1) · GLM 5.3 Flash on 4x 8 GB (1) · Qwen3.8 Flash Next on 2x 8 GB (Morrowmake EXL3) (1)

DeepSeek-V4.1-Flash-1017 (3) · DeepSeek-V4.1-Flash-1017 (748B in the Maya README) (1) · GLM-5.3-Flash (320B MoE, 18B active) (1) · Qwen3.8-Flash-Next (1)

EXL3 5.05 bpw; PLE (n-gram) table read from SSD (1) · Hybrid: routed experts EXL3 2.9 bpw (LibertAIDAI), everything else official FP8/BF16; KV BF16 (1) · Maya GGUF (Maya-S 340 GB or Maya-XS 277 GB; Engram tables stay on SSD) (1) · Official checkpoint (FP8 dense, FP4 experts); software FP8 on sm_80 (2) · W4A16 (INT4 weights, group size 128, FP16 activations): canada-quant/GLM-5.3-Flash-W4A16-MTP (1)

Morrowmake/vllm-cmp170hx (EXL3 path) (1) · Morrowmake/vllm-cmp170hx (vLLM fork, container image) (2) · Project Maya (Strata and llama.cpp lineage) (1) · vLLM PR #56201 head (79a7108d) plus the two Deepinfer-SM80 patches and 30 drop-in modules (2)

None (1) · Deepinfer-SM80 2a828fc lineage; vLLM v0.28.1rc0 base (1) · Deepinfer-SM80, vLLM v0.28.1rc0 base (1) · recipe 1.0.0, engine a0c57b5237 (1) · recipe 1.8.0, engine 819146023f (1) · tag qwen38-recipe-1.0.0, engine 18305948ac (1)

8 GB (6)

2 (2) · 4 (2) · 6 (1) · 8 (1)

engine-managed expert tiering across VRAM, host RAM and NVMe (1) · TP2 with expert parallel (1) · TP2 x PP3, partition 14,14,12 (1) · TP4 (default) or PP4 (1) · TP4 with expert parallel (96 whole experts per card) (1) · TP4 x PP2, partition 20,20 (1)

None (1) · 1,048,576 (2) · 262,144 (3)

0 - 500 (6)

None (1) · 2,651 (1) · 3,161 (1) · 3,463 (1) · 3,818 (1) · 4,037 (1)

64 GB (1) · 64 GiB (1) · 64 GiB exposed, --gpu-memory-utilization 0.95 (2) · 64 GiB, --gpu-memory-utilization 0.95 (2)

None (4) · 180 W (2)

None (4) · NVIDIA 580 or newer; P2P needs the Morrowmake/cmpunlocker build (2)

None (4) · cmpunlocker (64 GiB, 74 SMs); Morrowmake/cmpunlocker for P2P (2)

Proven (1) · Reported (5)

nathang6866 · voidgiraffe · HalfVulpes · 1a2b3c0967 · 68x0 · alanoo · anoane · c133 · CurtisAccelerate · darkmaniac7 · dufrelic · greencandle9753 · iIIusi0n · kellertreppe123 · matstatman · mrmannyatx · nestaa51 · pcsv. · plean. · reala7096 · shirogeek · vektor_prime · wgkbfcp · ZackO2o · Zanooda · Other · None

October 16, 2026 (2) · October 24, 2026 (1) · October 25, 2026 (1) · October 28, 2026 (2)

https://github.com/HalfVulpes/Deepinfer-SM80 (2) · https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe (1) · https://github.com/Morrowmake/glm53-flash-cmp170hx-recipe (1) · https://github.com/Morrowmake/qwen38-flash-next-cmp170hx-recipe (1) · https://github.com/mw00/project-maya#how-fast-is-it (1)