Kimi K3 GGUF IQ1_S lands on Hugging Face as 1-bit and 2-bit fixes continue

victormustar · x · 2026-07-28

A Hugging Face release is pushing a Kimi K3 GGUF IQ1S build while working on 2-bit and 1-bit fixes in parallel. The post notes that, to run it in llama.cpp, a related PR still needs to be fixed and merged first.

In other words, this is a local-deployment update: the quantized model files are being prepared, but the llama.cpp integration is still waiting on upstream changes.

Original post →

More from Infra

Infra channel →