Argonautlabs
Joined 1 month ago
Karma
187
Submissions
34
Member since
Sep 8
Recent submissions
Comment · 1 month ago
Its all about AI these days.
Comment · 1 month ago
Different angle on the same model: the full GLM-5.3 (744B MoE, 4-bit experts, 434 GB on disk) runs on a single MacBook Pro M5 Max with 128 GB
by streaming the experts from NVMe SSDs instead of keeping them in memory.
One drive gives about 2 tok/s; striped across four drives it reaches 3.5 tok/s with byte-identical output, and our best internal build with a not-yet-published patch does 4.2.
Method and numbers: https://github.com/argonautlabsai/argodrive (built on antirez/ds4).
Comment · 1 month ago
We stream DeepSeek-V4.1-Flash (518 GB, 4-bit) from NVMe on a 128 GB M5 Max, because it doesn't fit in RAM.
prompt processing steady decode
upstream, internal 16.23 10.59
ours, internal only 28.04 1.73x 14.38 1.36x
ours, +1 external 36.88 2.27x 16.05 1.52x
ours, +2 external 43.62 2.69x 17.38 1.64x
The first fork row is the one that matters: same single internal SSD, no replicas, no enclosures.Comment · 1 month ago
44 t/s prefill and 17 t/s decode on M5 Max 128gb Deep Seek V4.1 Flash (4 bit)