Can I run Phi-4-mini?

3.8B with 128K context — a capable little reasoner for light rigs.

reasoninggeneralchat · sizes: 3.8B · MIT

What runs it

machine	best fit	verdict	speed
Apple M1 · 8GB	3.8B Q8_0	🐢 CPU-only (slow)	1–2 tok/s
Apple M1 Pro · 16GB	3.8B Q8_0	✅ Runs comfortably	20–35 tok/s
Apple M2 · 16GB	3.8B Q8_0	✅ Runs comfortably	12–20 tok/s
Apple M3 Pro · 18GB	3.8B Q8_0	✅ Runs comfortably	17–30 tok/s
Apple M2 Pro · 32GB	3.8B Q8_0	✅ Runs comfortably	20–35 tok/s
Apple M4 Pro · 48GB	3.8B Q8_0	✅ Runs comfortably	30–45 tok/s
Apple M3 Max · 36GB	3.8B Q8_0	✅ Runs comfortably	35–60 tok/s
Apple M2 Max · 64GB	3.8B Q8_0	✅ Runs comfortably	35–60 tok/s
Apple M4 Max · 128GB	3.8B Q8_0	✅ Runs comfortably	45–75 tok/s
Apple M2 Ultra · 192GB	3.8B Q8_0	✅ Runs comfortably	50–80 tok/s
NVIDIA GeForce RTX 3060 · 12GB VRAM	3.8B Q8_0	✅ Runs comfortably	30–50 tok/s
NVIDIA GeForce RTX 4070 · 12GB VRAM	3.8B Q8_0	✅ Runs comfortably	45–70 tok/s
NVIDIA GeForce RTX 4090 · 24GB VRAM	3.8B Q8_0	✅ Runs comfortably	85–140 tok/s
NVIDIA GeForce RTX 5080 · 16GB VRAM	3.8B Q8_0	✅ Runs comfortably	80–140 tok/s
NVIDIA GeForce RTX 5090 · 32GB VRAM	3.8B Q8_0	✅ Runs comfortably	150–250 tok/s
AMD Radeon RX 7900 XTX · 24GB VRAM	3.8B Q8_0	✅ Runs comfortably	75–130 tok/s