Use the filters below to narrow your results.
page:
model:
quant:
engine:
engine version:
cards:
card count:
topology:
(Click arrow to add another value)
single card ·
engine-managed expert tiering across VRAM, host RAM and NVMe ·
engine-managed split with expert tiering across VRAM, RAM and NVMe ·
layer split (no tensor parallel), no P2P ·
PP2 (layer partition 25,23), no P2P ·
PP2 with PLE CPU offload ·
PP2, MTP 3, no P2P ·
PP2, MTP depth 3 ·
PP3 ·
PP3, no P2P (works at PP2 on two cards) ·
PP8 (also PP9 and PP10), TP1 ·
PP8, partition 5,5,5,5,5,5,5,5 ·
PP8, TP1 ·
TP2 over NCCL (GPU P2P), DFlash2 K7 plus hybrid drafting ·
TP2 with expert parallel ·
TP2 with whole-expert expert parallel ·
TP2 x PP3, partition 14,14,12 ·
TP4 ·
TP4 (default) or PP4 ·
TP4 (default) or PP4 for x1/x4 links ·
TP4 (P2P on); expert parallel off ·
TP4 with expert parallel (96 whole experts per card) ·
TP4 with expert parallel, MTP 3 ·
TP4 x PP2, partition 20,20 ·
TP4, P2P on ·
TP4, peer access off (NCCL_P2P_DISABLE=1), host all-reduce ·
TP5 across four CMP 170HX and one RTX PRO 6000 Blackwell (native backend, reduces through host memory); MTP draft on the PRO ·
TP6 (virtual-head padding), PP1 ·
Other ·
None
context:
decode tps:
prefill tps:
vram per card:
(Click arrow to add another value)
64 GB ·
64 GiB ·
64 GiB exposed, --gpu-memory-utilization 0.95 ·
64 GiB, --gpu-memory-utilization 0.95 ·
64 GB, --gpu-memory-utilization 0.94, TB_TORCH_MEM_CAP_GIB=61.5 ·
64 GB, --gpu-memory-utilization 0.95 ·
64 GB; weights 35.9 GB per rank (ranks 1-6), 37.6 GB rank 0, 46.3 GB rank 7 ·
64 GiB (64,911 MiB usable), GPU_MEMORY_UTILIZATION 0.98 ·
64 GiB, --gpu-memory-utilization 0.90 ·
64 GiB, --gpu-memory-utilization 0.92 (miner co-resident) ·
64 GiB, --gpu-memory-utilization 0.95 (fixed) ·
64 GiB, --gpu-memory-utilization 0.96 ·
64 GiB, --gpu-memory-utilization 0.97 ·
64 GiB, gpu-memory-utilization 0.92 ·
64 GiB, GPU_MEMORY_UTILIZATION 0.95 ·
64 GiB, GPU_UTIL 0.95 (fixed) ·
64 GiB, GPU_UTIL 0.96 at PP8 ·
64 GiB; weights 45.5 GiB plus 10 GiB KV per card; GPU_UTIL 0.94 (fixed) ·
64 GiB; weights PP0 39.48 GiB, PP1 45.53 GiB; --gpu-memory-utilization 0.9 ·
about 58 GiB of 64 GiB (116.6 GiB resident across both) ·
about 62.5 GB used of 64 GB, --gpu-memory-utilization 0.97 ·
about 62.9 / 62.3 GiB idle, peaks about 64.4 / 63.0 GiB with vision ·
gpu_split 58 GB per CMP, 70 GB on the PRO ·
Other ·
None
power cap:
driver:
unlock build:
status:
tested by:
tested on:
source:
(Click arrow to add another value)
Showing below up to 1 result in range #1 to #1.
& vram per card:
64 GB