local-llm — AI Digest

8 июн Google DeepMind Releases Gemma 4 QAT Checkpoints: Sub-1 GB On-Device E2B Model Google DeepMind models-llm
28 авг Ollama v0.33.2 (pre-release) restores system dark mode and keeps the proxy live across catalog changes Ollama tools
15 мая Ollama v0.24.0: Codex App Integration and MLX Sampler Improvements Ollama tools
16 мая llama.cpp b9161/b9169: Codex CLI Compatibility and Qwen3A Multimodal Support ggml-org tools
9 июн Ollama v0.30.7: Hermes Desktop Support, Gemma 4 QAT, and Nemotron-3-Ultra Ollama tools
11 июн llama.cpp b9589–b9592: CUDA SSM Sync Fix and Mamba Memory Optimization tools
17 июн Ollama v0.30.9: Cohere2Moe Support, Coding Agent Single-Token Output Bug Fixed tools
17 июн llama.cpp June 16 Builds: Eagle3 Speculative Decoding, Vulkan UMA Memory, NVFP4 Fixes tools
2 июл Ollama v0.31.1: Gemma 4 Nearly 90% Faster on Apple Silicon via MTP Ollama tools
8 июл Ollama v0.31.2: MLX small-batch matmul kernel, llama.cpp build 9840, CUDA updates tools
19 авг llama.cpp ships v0.1.2 pre-release plus daily b10483–b10488 with SYCL perf fix, OpenVINO bump, DGX Spark CUDA tuning llama.cpp (GGML) tools
27 авг Ollama v0.33.1 adds Qwen3.8 Flash Next support and structured-output mlxrunner Ollama tools
15 сен llama.cpp v0.4.1 adds Maple 20B, Tencent Hy 4, and Spark2.5 support ggml tools
17 сен llama.cpp patches remotely exploitable use-after-free in llama-server RPC endpoint ggml tools
24 сен llama.cpp v0.5.0 stable: CUDA/Metal kernel work, video_url in server tools
24 сен Ollama v0.34.4 pre-release fixes model-not-found flake, thinking-model structured outputs tools