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 > cards: 8 GB & tested by : darkmaniac7 or greencandle9753

Use the filters below to narrow your results.

page:
DeepSeek V4.1 Flash heretic on 4x 8 GB (1) · DeepSeek V4.1 Flash on 4x 8 GB (GNmac) (1)
model:
DeepSeek-V4.1-Flash-1017 (1) · DeepSeek-V4.1-Flash-1017 heretic (pqhaz abliteration) (1)
quant:
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 with the 38 heretic attn.wo_b tensors (1)
engine:
Morrowmake/vllm-cmp170hx (vLLM fork, container image) (1) · vLLM with a pinned sm_80 patch stack (built locally from source) (1)
engine version:
recipe 1.0.0 (commit d4d1f525), engine a0c57b52 (1) · recipe 1.2.0 (1)
cards: (Click arrow to add another value)
card count:
4 (2)
topology:
TP4 (1) · TP4 (default) or PP4 for x1/x4 links (1)
context:
262,144 (1) · 262,144 (up to 1,048,576) (1)
decode tps:
158 (1) · 258 (1)
prefill tps:
2,416 (1) · 2,453 (1)
vram per card:
64 GiB, --gpu-memory-utilization 0.92 (miner co-resident) (1) · 64 GiB, GPU_MEMORY_UTILIZATION 0.95 (1)
power cap:
None (1) · 180 W (nvidia-smi -pl 180) (1)
driver:
None (1) · CUDA 13 capable; measured on 610.43.02 (1)
unlock build:
None (1) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable driver for TP4 (1)
status:
Proven (1) · Reported (1)
tested by: (Click arrow to add another value)
tested on:
October 26, 2026 (1) · October 29, 2026 (1)
source:
https://github.com/GNmac-lab/deepseek-v41-flash-1017-cmp170hx (1) · https://github.com/Morrowmake/dsv41-flash-cmp170hx-recipe (1)

Showing below up to 2 results in range #1 to #2.

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"