Drilldown: Recipe

DeepSeek V4.1 Flash on 2x 8 GB (Project Maya) (1) · GLM 5.3 Flash on 2x 8 GB (ExLlamaV3 layer split) (1) · GLM 5.3 Flash on 2x 8 GB (Project Maya) (1) · Qwen3.8 Flash Next on 2x 8 GB (Morrowmake EXL3) (1) · Qwen3.8 Flash Next on 2x 8 GB (Plean PP2) (1) · Qwen3.8 Flash Next on 2x 8 GB (vektorprime PP2) (1)

DeepSeek-V4.1-Flash-1017 (748B in the Maya README) (1) · GLM-5.3-Flash (320B MoE, 18B active) (1) · GLM-5.3-Flash (321B in the Maya README) (1) · Qwen3.8-Flash-Next (3)

AWQ INT4: cyankiwi/Qwen3.8-Flash-Next-AWQ-INT4; 95 GiB BF16 PLE table in host RAM (FP8 table optional) (1) · EXL3 3.05 bpw: turboderp/GLM-5.3-Flash-exl3 (1) · EXL3 5.05 bpw; PLE (n-gram) table read from SSD (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) · Mixed INT4 AutoRound (Minachist/Qwen3.8-Flash-Next-INT4-Mixed-AutoRound, about 65 GB) with the full BF16 PLE table on NVMe (1)

ExLlamaV3 1.5.4 (built for SM80) with a small OpenAI-compatible server (1) · Morrowmake/vllm-cmp170hx (EXL3 path) (1) · Project Maya (Strata and llama.cpp lineage) (1) · Project Maya (Strata and llama.cpp lineage, EXL3 loading, DFlash2 drafter) (1) · vLLM 0.29.1rc1 nightly plus the checkpoint author's patches (1) · vLLM nightly + PR #53899 (a5530b9) + the repo's patch scripts (1)

None (2) · 0.1.dev1+ga5530b90c.d20260829 (1) · Flun/glm53-flash-cmp170hx-exl3 at 5933112 (1) · tag qwen38-recipe-1.0.0, engine 18305948ac (1) · v1.0.6 (this row) (1)

8 GB (6)

2 (6)

engine-managed expert tiering across VRAM, host RAM and NVMe (1) · engine-managed split with expert tiering across VRAM, RAM and NVMe (1) · layer split (no tensor parallel), no P2P (1) · PP2 with PLE CPU offload (1) · PP2, MTP 3, no P2P (1) · TP2 with expert parallel (1)

None (2) · 262,144 (2) · 262,144 (256K in the post) (1) · 392,960 (profile q8_384k) (1)

0 - 200 (6)

None (3) · 514 (1) · 2,651 (1) · 5,800 (1)

64 GB (3) · 64 GiB, --gpu-memory-utilization 0.95 (1) · 64 GiB; weights PP0 39.48 GiB, PP1 45.53 GiB; --gpu-memory-utilization 0.9 (1) · about 58 GiB of 64 GiB (116.6 GiB resident across both) (1)

None · 180 W · 200 W · 140 W · 140 W (200 W observed-draw abort guard) · 150 W per CMP (PRO 400 W) · 170 W (author's 10-card run) · 180 W (author's cards); about 170 W with a modest memory OC in his Discord numbers · 180 W (nvidia-smi -pl 180) · 180 W (one card unstable at 250 W) · Other

None (6)

None (6)

Proven (1) · Reported (5)

68x0 (1) · pcsv. (1) · plean. (1) · vektor_prime (1) · voidgiraffe (1) · ZackO2o (1)

August 2026 (1) · October 2026 (4)

https://github.com/Flun/glm53-flash-cmp170hx-exl3 (1) · https://github.com/Morrowmake/qwen38-flash-next-cmp170hx-recipe (1) · https://github.com/mw00/project-maya#how-fast-is-it (2) · https://github.com/vektorprime/qwen38-flash-next-pp2 (1) · https://www.bozocentral.com/2x-cmp170hx-qwen3-flash-next (1)