Run Kimi K3 using 29 GB of RAM at 0.50 tok/s

Re:Run Kimi K3 using 29 GB of RAM at 0.50 tok/s by roundup on Friday July 31, 2026 @04:06PM (#49127974)

How does this project compare to https://github.com/gavamedia/deltafin ?

[ Parent | on HN ]

Re:Run Kimi K3 using 29 GB of RAM at 0.50 tok/s by chrisringrose on Saturday August 01, 2026 @01:59AM (#49131483)

Hi! I'm one of the deltafin devs. The biggest difference is that this is not actually a 100% "pure" uncut Kimi K3. This is requantized to 3-bit residual, whereas deltafin is the full real unaltered k3, through and through.

WASTE reads about 17 GB/token versus Deltafin’s 25.8 GB/pass—roughly. That's 34% less expert traffic, and some could argue a 34% reduction in quality.

[ Parent | on HN ]

Re:Run Kimi K3 using 29 GB of RAM at 0.50 tok/s by withinboredom on Saturday August 01, 2026 @09:52AM (#49134460)

Why quantize to int8 when k3 is int4? I could be wrong, but that’s what I remember seeing.

[ Parent | on HN ]