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 : greencandle9753 or voidgiraffe

Use the filters below to narrow your results.

page:
DeepSeek V4.1 Flash on 4x 8 GB (GNmac) (1) · DeepSeek V4.1 Flash on 4x 8 GB (Morrowmake) (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 (2) · GLM-5.3-Flash (320B MoE, 18B active) (1) · Qwen3.8-Flash-Next (1)
quant:
EXL3 5.05 bpw; PLE (n-gram) table read from SSD (1) · Hybrid: routed experts EXL3 (mostly 3 bpw, 2 bpw on layers 18-22) from LibertAI's 2.9 bpw pack; attention, shared experts, indexer and DSpark drafter official FP8; KV fp8_ds_mla (1) · Hybrid: routed experts EXL3 2.9 bpw (LibertAIDAI), everything else official FP8/BF16; KV BF16 (1) · W4A16 (INT4 weights, group size 128, FP16 activations): canada-quant/GLM-5.3-Flash-W4A16-MTP (1)
engine:
Morrowmake/vllm-cmp170hx (EXL3 path) (1) · Morrowmake/vllm-cmp170hx (vLLM fork, container image) (2) · vLLM with a pinned sm_80 patch stack (built locally from source) (1)
engine version:
recipe 1.0.0, engine a0c57b5237 (1) · recipe 1.2.0 (1) · recipe 1.8.0, engine 819146023f (1) · tag qwen38-recipe-1.0.0, engine 18305948ac (1)
cards:
8 GB (4)
card count:
2 (1) · 4 (3)
topology:
TP2 with expert parallel (1) · TP4 (default) or PP4 (1) · TP4 (default) or PP4 for x1/x4 links (1) · TP4 with expert parallel (96 whole experts per card) (1)
context:
262,144 (3) · 262,144 (up to 1,048,576) (1)
decode tps:
152.6 (1) · 258 (1) · 287 (1) · 442.1 (1)
prefill tps:
2,416 (1) · 2,651 (1) · 3,161 (1) · 3,818 (1)
vram per card:
64 GiB exposed, --gpu-memory-utilization 0.95 (2) · 64 GiB, --gpu-memory-utilization 0.95 (1) · 64 GiB, GPU_MEMORY_UTILIZATION 0.95 (1)
power cap:
None (1) · 180 W (2) · 180 W (nvidia-smi -pl 180) (1)
driver:
None (1) · CUDA 13 capable; measured on 610.43.02 (1) · NVIDIA 580 or newer; P2P needs the Morrowmake/cmpunlocker build (2)
unlock build:
None (1) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable driver for TP4 (1) · cmpunlocker (64 GiB, 74 SMs); Morrowmake/cmpunlocker for P2P (2)
status:
Proven (2) · Reported (2)
tested by: (Click arrow to add another value)
tested on:
October 16, 2026 (2) · October 24, 2026 (1) · October 26, 2026 (1)
source:
https://github.com/GNmac-lab/deepseek-v41-flash-1017-cmp170hx (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)

Showing below up to 4 results in range #1 to #4.

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"