compatibility
Benchmarking across some of our published families
You’re running a local assistant on a 16 GB card, or you’ve got two of them, and you’re trying to decide which model family to live with. That’s who this is for. Over the last few days I ran the unified benchmark suite against five of the tiered model families we publish. Same hardware, same flags, one variable: the model file. Here’s what came out, and what I think it’s telling us.
Posted by 
Aalias "Empathy-as-Code" on Friday, November 13, 2026
esatapedico (Raff Martin)
I build software for the people whose hardware is almost good enough. Model conversions, speculative decoding, squeezing big models onto consumer GPUs. Everything I ship is free and Apache-2.0.