← All creators
J
Jon Saad-Falcon
0 recommended products
Everything Jon personally uses, recommends, or has created — plus things they don't recommend — sourced from their own show and appearances on other podcasts.
Recent episodes
All →Showing 4 of 4 products
Clear filtersMentioned in 1 episode
"We did about 20 plus different state-of-the-art local models across Gemma, GPT OSS, Qwen, IBM Granite, all in the range of one to 200 billion parameters."
Mentioned in 1 episode
"We did about 20 plus different state-of-the-art local models across Gemma, GPT OSS, Qwen, IBM Granite, all in the range of one to 200 billion parameters."
Mentioned in 1 episode
"The 18x improvement in intelligence delivered per joule is primarily driven by better accelerators — by more memory being placed on consumer GPUs such as the Apple M4 Max as well as the DGX Spark from Nvidia."
Mentioned in 1 episode
"There are even more specialized accelerators for inference such as the Samanova SN40L for which consumer accelerators are lagging even more behind."
0 recommended · 0 sponsored · 0 warned against · 0 episodes