Topic
Llama.cpp
3 stories tagged Llama.cpp, newest first.
Aug 20, 2026, 4:52 PMArtificial Intelligence
Liquid AI DSpark Speeds LFM2.5 Inference Up to 3.18x
Liquid AI's DSpark checkpoints boost LFM2.5 inference up to 3.18x on H100 and 2.87x on M4 Max, while preserving identical greedy outputs across five tests.
DateSectionHeadlineSource
Aug 19
Artificial Intelligence
Liquid AI LFM2.5 QAD Q4_0 Models Recover 97% of BF16 Accuracy
Hugging Face - Blog
▲
Aug 10
Artificial Intelligence
Meta Launches Muse Glimmer, a 30B Open Source Multimodal Agent
Hugging Face - Blog