Model Releases
There were some exceptionally cool demos from @ollama and omlx using MLX to run Qwen 3.5 and Gemma 4 on Apple silicon. The capabilities of l…
There were some exceptionally cool demos from @ollama and omlx using MLX to run Qwen 3.5 and Gemma 4 on Apple silicon. The capabilities of local LLMs and the surrounding ecosystem have come a long way
There were some exceptionally cool demos from @ollama and omlx using MLX to run Qwen 3.5 and Gemma 4 on Apple silicon. The capabilities of local LLMs and the surrounding ecosystem have come a long way in the past couple years. Watching @awnihannun at @ollama
Related
- mlx @ollama!
- Google's Gemma 4 is pretty wild. You can now run it locally with OpenClaw in 3 steps. 1. Install Ollama 2. Pull Gemma 4 model 3. Launch Open…
- Lots of love for Gemma 4! Team just told me it’s already had 10M+ downloads since last week’s launch. Gemma models have now been downloaded …
- Gemma 4:e4b offloads to RAM despite having just half of VRAM used.
- See you there!
Source: Ollama (X) | 2026-04-10