HackerTrans
TopNewTrendsCommentsPastAskShowJobs

alexandercheema

no profile record

Submissions

Kimi K2.5 on 2 Mac Studios (<$20K) running at 24 TPS

twitter.com
6 points·by alexandercheema·6 tháng trước·4 comments

Clustering Nvidia DGX Spark and M3 Ultra Mac Studio for 4x Faster LLM Inference

twitter.com
8 points·by alexandercheema·9 tháng trước·1 comments

Clustering Nvidia DGX Spark and M3 Ultra Mac Studio for 4x Faster LLM Inference

blog.exolabs.net
5 points·by alexandercheema·9 tháng trước·0 comments

comments

alexandercheema
·4 tháng trước·discuss
lol bro there is already a big OSS project called exo: https://github.com/exo-explore/exo
alexandercheema
·5 tháng trước·discuss
Isn't Claude Code for Infrastructure just...Claude Code?
alexandercheema
·6 tháng trước·discuss
Is there one for Kimi K2.5?
alexandercheema
·9 tháng trước·discuss
Appreciate you checking back so often. We have some exciting plans. Keep checking and it won't be long before something pops up :)
alexandercheema
·9 tháng trước·discuss
Yes, these models are mostly compute-bound so benefit even more from the compute on the DGX Spark.
alexandercheema
·9 tháng trước·discuss
Blog author here. Actually, no. The model can be streamed into the DGX Spark, so we can run prefill of models much larger than 128GB (e.g. DeepSeek R1) on the DGX Spark. This feature is coming to EXO 1.0 which will be open-sourced soonTM.