On this day: Jun 5
3 records from this date, 2025 to 2026, gathered year by year — the most recent year first.
2026
This year · 1 recordOllama 0.30 adds llama.cpp-based GGUF compatibility to its MLX engineOllama
The local deployment stack reorganized from sole reliance on llama.cpp to MLX first + GGUF compatibility
On-Device & Local InferenceOfficial
2025
1 year ago · 2 recordsCommon Pile v0.1Kandpal et al.
The data-side response to litigation risk; reached Llama 1 and 2 7B-class performance with openly licensed data alone
Alibaba Qwen releases the Qwen3 Embedding and Reranker series (0.6B–8B)Alibaba Qwen
The point where open-weight embeddings overtook commercial API models on the leaderboard
Embeddings & Vector SearchOfficial