Drilldown: Recipe - CMP Wiki

Jump to content

Choose a table:

Recipe > tested by

: pcsv.

or reala7096

or voidgiraffe

Use the filters below to narrow your results.

DeepSeek V4.1 Flash on 2x 8 GB (Project Maya) (1) · DeepSeek V4.1 Flash on 4x 8 GB (Morrowmake) (1) · GLM 5.3 Flash on 4x 8 GB (1) · GLM 5.3 on 8x 8 GB (vllm-170hx-glm5) (1) · Qwen3.8 Flash Next on 2x 8 GB (Morrowmake EXL3) (1)

DeepSeek-V4.1-Flash-1017 (1) · DeepSeek-V4.1-Flash-1017 (748B in the Maya README) (1) · GLM-5.3 (full 78-layer DSA MoE, not Flash) (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) · GLM-5.3-Int4-Int8Mix-AWQ-g64; drafter incoai/GLM-5.3-DFlash2 (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) · 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) · Morrowmake/vllm-cmp170hx branch ampere-glm53 plus fail-closed source patches (1) · Project Maya (Strata and llama.cpp lineage) (1)

None (1) · recipe 1.0.0, engine a0c57b5237 (1) · recipe 1.8.0, engine 819146023f (1) · tag qwen38-recipe-1.0.0, engine 18305948ac (1) · vLLM 0.30.1rc1, fork commit 378c37b0 (1)

8 GB (5)

2 (2) · 4 (2) · 8 (1)

engine-managed expert tiering across VRAM, host RAM and NVMe (1) · PP8 (also PP9 and PP10), TP1 (1) · TP2 with expert parallel (1) · TP4 (default) or PP4 (1) · TP4 with expert parallel (96 whole experts per card) (1)

None (1) · 1,048,576 per request (1) · 262,144 (3)

48.7 (1) · 63 (1) · 152.6 (1) · 287 (1) · 442.1 (1)

None (1) · 1,833 (1) · 2,651 (1) · 3,161 (1) · 3,818 (1)

64 GB (1) · 64 GiB exposed, --gpu-memory-utilization 0.95 (2) · 64 GiB, --gpu-memory-utilization 0.95 (1) · 64 GiB, GPU_UTIL 0.96 at PP8 (1)

None (2) · 170 W (author's 10-card run) (1) · 180 W (2)

None (3) · NVIDIA 580 or newer; P2P needs the Morrowmake/cmpunlocker build (2)

None (3) · cmpunlocker (64 GiB, 74 SMs); Morrowmake/cmpunlocker for P2P (2)

Proven (2) · Reported (3)

September 29, 2026 (1) · October 16, 2026 (2) · October 24, 2026 (1) · October 25, 2026 (1)

https://github.com/arvkmr/vllm-170hx-glm5 (1) · 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)

Showing below up to 5 results in range #1 to #5.

D

G

Q

Qwen3.8 Flash Next on 2x 8 GB (Morrowmake EXL3)

Retrieved from "https://cmp.wiki/wiki/Special:Drilldown/Recipe"