🐧 PenguinPulse

Linux Graphics & Gaming News

Articles tagged: mlx

← Back to all articles

Ollama v0.30.0-rc17 Shifts to llama.cpp, GGUF, Adds MLX for Apple Silicon

Ollama has recently released v0.30.0-rc17, a pre-release introducing a significant architectural overhaul. This version "will change the architecture to directly support llama.cpp instead of building ...

Read more →

Ollama v0.23.1 Accelerates Gemma 4 MLX Inference with MTP Speculative Decoding

Ollama has released version 0.23.1, introducing Gemma 4 Multi-token Processing (MTP) speculative decoding for its MLX runner. This update, primarily benefiting macOS users with Apple Silicon, can prov...

Read more →

Ollama v0.21.1 Adds Kimi CLI, Enhances MLX Runner Performance and Features

Ollama released version 0.21.1 recently, introducing the Kimi CLI for local AI model execution. Users can now launch the Kimi CLI via Ollama, which "excels at long horizon agentic execution tasks thro...

Read more →

Ollama v0.17.5 Adds Qwen 3.5 Models, Fixes GPU/CPU Split & MLX Crashes

Ollama v0.17.5 was released today, introducing support for the Qwen 3.5 small model series, now available in 0.8B, 2B, 4B, and 9B parameter sizes. This update addresses several critical issues, includ...

Read more →