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 > status: Reported & tested by : CurtisAccelerate or nathang6866

Use the filters below to narrow your results.

page:
DeepSeek V4.1 Flash on 4x 8 GB (CurtisAccelerate TC-MoE) (1) · MiMo V2.6 Flash on 4x 8 GB (1) · Qwen3.8 Flash Next on 1x 8 GB (ElectroHobo 3 bpw) (1)
model:
DeepSeek-V4.1-Flash-1017 (1) · MiMo-V2.6-Flash-RL (309B MoE, 15B active; text, image, video and audio input) (1) · Qwen3.8-Flash-Next (125B MoE per the recipe) (1)
quant:
AutoRound mixed 2/3-bit (klee100, 2.998 effective bpw, 47 GiB on card) plus halt95's FP8 n-gram table in host RAM (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) · NVFP4 (ModelOpt mixed precision): ProCreations/MiMo-V2.6-Flash-RL-NVFP4, run as 4-bit weights with BF16 activations through Marlin (1)
engine:
Morrowmake/vllm-cmp170hx (bind-mounted sm80 package) plus the author's tensor-core MoE kernels (1) · Morrowmake/vllm-cmp170hx image (tag qwen38-recipe-1.0.0) plus one mounted file (vLLM #58235 vision-sink fix) (1) · Morrowmake/vllm-cmp170hx image with patch files mounted read-only (1)
engine version:
recipe 0.2.1; engine 18305948ac (2) · vllm-cmp170hx 18305948ac; TC-MoE fb9786ec (1)
cards:
8 GB (3)
card count:
1 (1) · 4 (2)
topology:
single card (1) · TP4 (P2P on); expert parallel off (1) · TP4, peer access off (NCCL_P2P_DISABLE=1), host all-reduce (1)
context:
1,048,576 (1) · 262,144 (1) · 262,144 (weights address 1,048,576) (1)
decode tps:
144.2 (1) · 274.9 (1) · 296.4 (1)
prefill tps:
1,523 (1) · 2,722 (1) · 4,243 (1)
vram per card:
64 GiB, --gpu-memory-utilization 0.95 (fixed) (1) · 64 GiB; weights 45.5 GiB plus 10 GiB KV per card; GPU_UTIL 0.94 (fixed) (1) · about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 (1)
power cap:
140 W (1) · 180 W (2)
driver:
None (1) · 580 or newer (measured on 610.57.04) (2)
unlock build:
None (1) · cmpunlocker (64 GiB, 74 SMs) (1) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable build (1)
status: (Click arrow to add another value)
tested by: (Click arrow to add another value)
tested on:
October 18, 2026 (1) · October 22, 2026 (1) · October 23, 2026 (1)
source:
https://github.com/CurtisAccelerate/DeepSeekv41-Flash-1017-EXL3-CMP170HX (1) · https://github.com/ElectroHobo/mimo-v26-flash-cmp170hx-recipe (1) · https://github.com/ElectroHobo/qwen38-flash-next-3bpw-1x-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"