Can I run Ministral 3 14B?

chatcodinggeneral · sizes: 14B

What runs it

machine	best fit	verdict	speed
Apple M1 · 8GB	14B Q4_K_M	❌ Won't fit	—
Apple M1 Pro · 16GB	14B Q4_K_M	🐢 CPU-only (slow)	2–3 tok/s
Apple M2 · 16GB	14B Q4_K_M	🐢 CPU-only (slow)	0.9–1 tok/s
Apple M3 Pro · 18GB	14B Q8_0	🐢 CPU-only (slow)	0.7–1 tok/s
Apple M2 Pro · 32GB	14B Q8_0	✅ Runs (tight)	7–12 tok/s
Apple M4 Pro · 48GB	14B Q8_0	✅ Runs comfortably	10–17 tok/s
Apple M3 Max · 36GB	14B Q8_0	✅ Runs comfortably	13–20 tok/s
Apple M2 Max · 64GB	14B Q8_0	✅ Runs comfortably	13–20 tok/s
Apple M4 Max · 128GB	14B Q8_0	✅ Runs comfortably	16–25 tok/s
Apple M2 Ultra · 192GB	14B Q8_0	✅ Runs comfortably	25–40 tok/s
NVIDIA GeForce RTX 3060 · 12GB VRAM	14B Q4_K_M	✅ Runs (tight)	18–30 tok/s
NVIDIA GeForce RTX 4070 · 12GB VRAM	14B Q4_K_M	✅ Runs (tight)	25–40 tok/s
NVIDIA GeForce RTX 4090 · 24GB VRAM	14B Q8_0	✅ Runs comfortably	30–50 tok/s
NVIDIA GeForce RTX 5080 · 16GB VRAM	14B Q4_K_M	✅ Runs comfortably	50–85 tok/s
NVIDIA GeForce RTX 5090 · 32GB VRAM	14B Q8_0	✅ Runs comfortably	55–90 tok/s
AMD Radeon RX 7900 XTX · 24GB VRAM	14B Q8_0	✅ Runs comfortably	25–45 tok/s