Apple silicon · 16 GB
A polished 4B–8B local experience when the OS and apps have enough headroom.
Qwen3 14B
The highest listed result may be a tight or offloaded fit. For daily use, prefer the first result marked Comodo and keep context modest.
MLX LM
Native Apple silicon inference, experimentation and fine-tuning. Only for Apple silicon. Use an MLX-converted model and tune KV cache size for long contexts. The bundled mlx_lm.server is an OpenAI-compatible HTTP endpoint (default 127.0.0.1:8080), but upstream warns it implements only basic security checks and is not recommended for production.
Apri guidaModelli open-weight rappresentativi
Qwen3 14B
- Memoria stimata
- ~11.2 GB
- Contesto
- 32K+
Gemma 3 12B
- Memoria stimata
- ~9.4 GB
- Contesto
- 128K
Qwen3 8B
- Memoria stimata
- ~6.8 GB
- Contesto
- 32K+
Qwen3 4B
- Memoria stimata
- ~3.6 GB
- Contesto
- 32K+
Gemma 3 4B
- Memoria stimata
- ~4.2 GB
- Contesto
- 128K
Llama 3.2 3B
- Memoria stimata
- ~2.8 GB
- Contesto
- 128K
Fit is based on estimated total model memory. Driver support, KV cache, multimodal projectors, concurrency, and desktop applications can all reduce available headroom. Current fit: Qwen3 14B (Al limite), Gemma 3 12B (Al limite), Qwen3 8B (Comodo), Qwen3 4B (Comodo), Gemma 3 4B (Comodo), Llama 3.2 3B (Comodo).