Model Releases
Got Meta's new Muse Glimmer 30B running on my MacBook (M3 Max, 96GG) and tested the serving options available so far. Fastest right now: Oll…
Got Meta's new Muse Glimmer 30B running on my MacBook (M3 Max, 96GG) and tested the serving options available so far. Fastest right now: Ollama's MLX engine (DFlash included) at ~29 tok/s. Tuned llama
Got Meta's new Muse Glimmer 30B running on my MacBook (M3 Max, 96GG) and tested the serving options available so far. Fastest right now: Ollama's MLX engine (DFlash included) at ~29 tok/s. Tuned llama.cpp: ~21. Raw mlx-vlm: ~10, not optimized yet. Numbers below if you're setting it up 👇
Related
- Muse Glimmer is now available to run with Ollama. Available today via Ollama’s MLX engine with state-of-the-art-performance on Apple Silicon…
- v0.32.7
- Tested Muse Glimmer locally on coding with OpenCode & agentic work
Source: Ollama (X) | 2026-08-10