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 > card count: 4 & decode tps: 120-300 & status: Reported

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 (CurtisAccelerate TC-MoE) (1) · DeepSeek V4.1 Flash on 4x 8 GB (Morrowmake) (1) · MiMo V2.6 Flash on 4x 8 GB (1)
model:
DeepSeek-V4.1-Flash-1017 (2) · DeepSeek-V4.1-Flash-1017 heretic (pqhaz abliteration) (1) · MiMo-V2.6-Flash-RL (309B MoE, 15B active; text, image, video and audio input) (1)
quant:
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) · Hybrid: routed experts EXL3 2.9 bpw (LibertAIDAI), everything else official FP8/BF16 with the 38 heretic attn.wo_b tensors (1) · Hybrid: routed experts EXL3 2.9 bpw (LibertAIDAI), everything else official FP8/BF16; KV BF16 (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 (vLLM fork, container image) (2) · Morrowmake/vllm-cmp170hx image (tag qwen38-recipe-1.0.0) plus one mounted file (vLLM #58235 vision-sink fix) (1)
engine version:
recipe 0.2.1; engine 18305948ac (1) · recipe 1.0.0 (commit d4d1f525), engine a0c57b52 (1) · recipe 1.0.0, engine a0c57b5237 (1) · vllm-cmp170hx 18305948ac; TC-MoE fb9786ec (1)
cards:
8 GB (4)
card count:
4 (4)
topology:
TP4 (1) · TP4 (P2P on); expert parallel off (1) · TP4 with expert parallel (96 whole experts per card) (1) · TP4, peer access off (NCCL_P2P_DISABLE=1), host all-reduce (1)
context:
1,048,576 (1) · 262,144 (2) · 262,144 (weights address 1,048,576) (1)
decode tps:
144.2 (1) · 158 (1) · 274.9 (1) · 287 (1)
prefill tps:
1,523 (1) · 2,453 (1) · 2,722 (1) · 3,818 (1)
vram per card:
64 GiB exposed, --gpu-memory-utilization 0.95 (1) · 64 GiB, --gpu-memory-utilization 0.92 (miner co-resident) (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:
None (1) · 140 W (1) · 180 W (2)
driver:
None (2) · 580 or newer (measured on 610.57.04) (1) · NVIDIA 580 or newer; P2P needs the Morrowmake/cmpunlocker build (1)
unlock build:
None (2) · cmpunlocker (64 GiB, 74 SMs) with a P2P-capable build (1) · cmpunlocker (64 GiB, 74 SMs); Morrowmake/cmpunlocker for P2P (1)
status: (Click arrow to add another value)
tested by:
CurtisAccelerate (1) · darkmaniac7 (1) · nathang6866 (1) · voidgiraffe (1)
tested on:
October 18, 2026 (1) · October 22, 2026 (1) · October 24, 2026 (1) · October 29, 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/Morrowmake/dsv41-flash-cmp170hx-recipe (2)

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"