LM Studio 0.4.24 adds advanced llama.cpp argument overrides for GGUF model loading
solyarisoftware · x · 2026-09-10
LM Studio 0.4.24 gives local AI power users more control over the underlying llama.cpp engine:
- New advanced llama.cpp argument overrides for GGUF loading: model-loading behavior, backend tuning, drafter configuration, and memory/context choices
- Improved compatibility heuristics for DSpark and DFlash assistant drafters
- Fixes incorrect context-length reporting and a multimodal API bug where text + image input could be split into separate user messages
A small release for most, but significant for hand-tuned local inference under an easy GUI.
More from Infra
- Keras ships ZeroModels: 100+ model families in pure Keras 3, runnable on any backend — fchollet · 2026-09-10
- Cohere moves to NVIDIA Blackwell, cutting token costs and TTFT by 30–50% — cohere · 2026-09-10
- Author uses local AI models to review book manuscripts for $0 in tokens — walkingriver · 2026-09-10
- Musk's Colossus data center fuels massive local backlash, reports Scientific American — scientificamerican · 2026-09-10
- Analyst: Huawei to undercut US AI stack with cheaper chips tuned for Chinese models — 2C_ornot2C · 2026-09-10
- Photon 2.2 Ships Optimized Local Inference for Ampere Through Blackwell GPUs — JFPuget · 2026-09-10