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 : CurtisAccelerate or pcsv. or vektor_prime

Use the filters below to narrow your results.

page:
DeepSeek V4.1 Flash on 2x 8 GB (Project Maya) (1) · DeepSeek V4.1 Flash on 4x 8 GB (CurtisAccelerate TC-MoE) (1) · Qwen3.8 Flash Next on 2x 8 GB (vektorprime PP2) (1)
model:
DeepSeek-V4.1-Flash-1017 (1) · DeepSeek-V4.1-Flash-1017 (748B in the Maya README) (1) · Qwen3.8-Flash-Next (1)
quant:
AWQ INT4: cyankiwi/Qwen3.8-Flash-Next-AWQ-INT4; 95 GiB BF16 PLE table in host RAM (FP8 table optional) (1) · Hybrid: LibertAI EXL3 2.9 bpw routed experts (layers 0-39), official FP8/FP4 for attention, shared experts, head, draft and Engram; KV fp8_ds_mla (1) · Maya GGUF (Maya-S 340 GB or Maya-XS 277 GB; Engram tables stay on SSD) (1)
engine:
Morrowmake/vllm-cmp170hx (bind-mounted sm80 package) plus the author's tensor-core MoE kernels (1) · Project Maya (Strata and llama.cpp lineage) (1) · vLLM nightly + PR #53899 (a5530b9) + the repo's patch scripts (1)
engine version:
None (1) · 0.1.dev1+ga5530b90c.d20260829 (1) · vllm-cmp170hx 18305948ac; TC-MoE fb9786ec (1)
cards:
8 GB (3)
card count:
2 (2) · 4 (1)
topology:
engine-managed expert tiering across VRAM, host RAM and NVMe (1) · PP2 with PLE CPU offload (1) · TP4, peer access off (NCCL_P2P_DISABLE=1), host all-reduce (1)
context:
None (1) · 262,144 (1) · 262,144 (weights address 1,048,576) (1)
decode tps:
63 (1) · 75.4 (1) · 144.2 (1)
prefill tps:
None (2) · 1,523 (1)
vram per card:
64 GB (1) · 64 GiB; weights PP0 39.48 GiB, PP1 45.53 GiB; --gpu-memory-utilization 0.9 (1) · about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 (1)
power cap:
None (2) · 140 W (1)
driver:
None (3)
unlock build:
None (3)
status:
Reported (3)
tested by: (Click arrow to add another value)
tested on:
August 2026 (1) · October 2026 (2)
source:
https://github.com/CurtisAccelerate/DeepSeekv41-Flash-1017-EXL3-CMP170HX (1) · https://github.com/mw00/project-maya#how-fast-is-it (1) · https://github.com/vektorprime/qwen38-flash-next-pp2 (1)

Showing below up to 3 results in range #1 to #3.

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"