Ollama 0.30.8 on Apple Silicon: MLX runner not active for GGUF models

A recent analysis of Ollama version 0.30.8 revealed that despite the binary containing code for an MLX runner, it does not appear to be utilized when running standard GGUF models on Apple Silicon. The investigation, conducted on an M1 Max 64GB Mac, found that logs consistently showed the `llama-server` as the active runner, even when testing different model architectures. This suggests that the claimed performance improvements from MLX may not apply to users running models via the typical `ollama pull` and `ollama run` commands. AI

IMPACT Investigating the actual backend used by local LLM runners like Ollama is crucial for optimizing performance on specific hardware.

RANK_REASON Technical analysis of a specific software version's functionality.

Read on dev.to — LLM tag →

• Apple M1 Max
• Apple Silicon
• GGUF
• llama.cpp
• MLX
• Ollama
• Qwen 3.5
• Qwen-3.6

• infra
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →