Jump to content
Toggle search
Toggle menu
CMP Wiki
Toggle preferences menu
Toggle personal menu
Not logged in
Your IP address will be publicly visible if you make any edits.

Drilldown: Recipe

More actions
Recipe > tested by : 68x0 or ZackO2o or voidgiraffe

Use the filters below to narrow your results.

page:
DeepSeek V4.1 Flash on 4x 8 GB (Morrowmake) (1) · GLM 5.3 Flash on 2x 8 GB (ExLlamaV3 layer split) (1) · GLM 5.3 Flash on 2x 8 GB (Project Maya) (1) · GLM 5.3 Flash on 4x 8 GB (1) · Qwen3.8 Flash Next on 2x 8 GB (Morrowmake EXL3) (1)
model:
DeepSeek-V4.1-Flash-1017 (1) · GLM-5.3-Flash (320B MoE, 18B active) (2) · GLM-5.3-Flash (321B in the Maya README) (1) · Qwen3.8-Flash-Next (1)
quant:
EXL3 3.05 bpw: turboderp/GLM-5.3-Flash-exl3 (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-M GGUF (116 GB), every expert in VRAM; Maya-S (96.5 GB) and Maya-S24 (94.7 GB) also reported (1) · W4A16 (INT4 weights, group size 128, FP16 activations): canada-quant/GLM-5.3-Flash-W4A16-MTP (1)
engine:
ExLlamaV3 1.5.4 (built for SM80) with a small OpenAI-compatible server (1) · Morrowmake/vllm-cmp170hx (EXL3 path) (1) · Morrowmake/vllm-cmp170hx (vLLM fork, container image) (2) · Project Maya (Strata and llama.cpp lineage, EXL3 loading, DFlash2 drafter) (1)
engine version:
Flun/glm53-flash-cmp170hx-exl3 at 5933112 (1) · recipe 1.0.0, engine a0c57b5237 (1) · recipe 1.8.0, engine 819146023f (1) · tag qwen38-recipe-1.0.0, engine 18305948ac (1) · v1.0.6 (this row) (1)
cards:
8 GB (5)
card count:
2 (3) · 4 (2)
topology:
engine-managed split with expert tiering across VRAM, RAM and NVMe (1) · layer split (no tensor parallel), no P2P (1) · TP2 with expert parallel (1) · TP4 (default) or PP4 (1) · TP4 with expert parallel (96 whole experts per card) (1)
context:
None (1) · 262,144 (3) · 392,960 (profile q8_384k) (1)
decode tps:
60 (1) · 61.3 (1) · 152.6 (1) · 287 (1) · 442.1 (1)
prefill tps:
None (1) · 514 (1) · 2,651 (1) · 3,161 (1) · 3,818 (1)
vram per card:
64 GB (1) · 64 GiB exposed, --gpu-memory-utilization 0.95 (2) · 64 GiB, --gpu-memory-utilization 0.95 (1) · about 58 GiB of 64 GiB (116.6 GiB resident across both) (1)
power cap:
None (3) · 180 W (2)
driver:
None (3) · NVIDIA 580 or newer; P2P needs the Morrowmake/cmpunlocker build (2)
unlock build:
None (3) · cmpunlocker (64 GiB, 74 SMs); Morrowmake/cmpunlocker for P2P (2)
status:
Proven (2) · Reported (3)
tested by: (Click arrow to add another value)
tested on:
October 16, 2026 (2) · October 20, 2026 (1) · October 24, 2026 (1)
source:
https://github.com/Flun/glm53-flash-cmp170hx-exl3 (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.

View (previous 250 | next 250) (20 | 50 | 100 | 250 | 500)


View (previous 250 | next 250) (20 | 50 | 100 | 250 | 500)

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