BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

llama.cpp Adds Gemma 4 DSpark Draft Support

Sep 23, 2026, first seen via Training & inference tooling releases

llama.cpp release b11132 added GGUF conversion and runtime support for Gemma 4 DSpark draft models.

Read the original at github.comOpens the publisher's site in a new tab

Also covering this

b11130github.com, Sep 23

More in Open-weight & owned stack

Kyutai Releases Voice Of Reason CheckpointsSep 23Xiaomi Releases MiMo-V2.6 Open-Weight Model FamilySep 22Intrinsic open-sources Core robotics software infrastructureSep 22Harvey Launches Kimi-Based In-House ModelSep 21Kimi K3 Reaches AWS And Alibaba Cloud PlatformsSep 21