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 : c133 or pcsv. or wgkbfcp

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 6x 8 GB (TP6) (1) · Qwen3.8 Flash Next on 3x 8 GB (clee PP3) (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:
Maya GGUF (Maya-S 340 GB or Maya-XS 277 GB; Engram tables stay on SSD) (1) · Official checkpoint: dense MXFP8 through an SM80 Marlin W8A16 path, routed experts MXFP4 through W4A16; KV FP8 (1) · W4A16 AutoRound: Intel/Qwen3.8-Flash-Next-W4A16-AutoRound; 95.4 GiB BF16 PLE table streamed from NVMe; KV fp8 e4m3 (software-decoded on SM80) (1)
engine:
Custom SM80 vLLM (patched from public commit 79a7108d9) (1) · Project Maya (Strata and llama.cpp lineage) (1) · vLLM nightly 7d0b4e57 plus the author's pure-Python fork clee/vllm-sm80 (branch q38fn/stack) (1)
engine version:
None (1) · q38fn/stack on nightly-7d0b4e57 (1) · reports 0.0.0; patches/public-base-to-runtime.patch (109 files) (1)
cards:
8 GB (3)
card count:
2 (1) · 3 (1) · 6 (1)
topology:
engine-managed expert tiering across VRAM, host RAM and NVMe (1) · PP3, no P2P (works at PP2 on two cards) (1) · TP6 (virtual-head padding), PP1 (1)
context:
None (1) · 1,048,576 (1) · 1,048,576 (YaRN x4) (1)
decode tps:
63 (1) · 74.4 (1) · 78.55 (1)
prefill tps:
None (2) · 4,831 (1)
vram per card:
64 GB (1) · 64 GB, --gpu-memory-utilization 0.95 (1) · 64 GiB, gpu-memory-utilization 0.92 (1)
power cap:
None (3)
driver:
None (3)
unlock build:
None (3)
status:
Proven (1) · Reported (2)
tested by: (Click arrow to add another value)
tested on:
October 10, 2026 (1) · October 19, 2026 (1) · October 25, 2026 (1)
source:
https://github.com/clee/qwen3.8-flash-next-3x170hx (1) · https://github.com/mw00/project-maya#how-fast-is-it (1) · https://github.com/wgkbfcp/deepseek-v4.1-flash-1017-cmp170hx-recipe (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"