Can I run StarCoder2?

BigCode's permissive code models trained on The Stack v2.

coding · sizes: 3B, 7B, 15B · BigCode OpenRAIL-M

What runs it

machine	best fit	verdict	speed
Apple M1 · 8GB	3B Q4_K_M	✅ Runs (tight)	19–30 tok/s
Apple M1 Pro · 16GB	7B Q8_0	✅ Runs (tight)	13–20 tok/s
Apple M2 · 16GB	7B Q8_0	✅ Runs (tight)	7–12 tok/s
Apple M3 Pro · 18GB	15B Q3_K_M	✅ Runs (tight)	10–16 tok/s
Apple M2 Pro · 32GB	15B Q8_0	✅ Runs (tight)	6–10 tok/s
Apple M4 Pro · 48GB	15B Q8_0	✅ Runs comfortably	8–14 tok/s
Apple M3 Max · 36GB	15B Q8_0	✅ Runs (tight)	10–17 tok/s
Apple M2 Max · 64GB	15B Q8_0	✅ Runs comfortably	11–18 tok/s
Apple M4 Max · 128GB	15B Q8_0	✅ Runs comfortably	13–20 tok/s
Apple M2 Ultra · 192GB	15B Q8_0	✅ Runs comfortably	14–25 tok/s
NVIDIA GeForce RTX 3060 · 12GB VRAM	15B Q4_K_M	✅ Runs (tight)	14–25 tok/s
NVIDIA GeForce RTX 4070 · 12GB VRAM	15B Q4_K_M	✅ Runs (tight)	20–35 tok/s
NVIDIA GeForce RTX 4090 · 24GB VRAM	15B Q8_0	✅ Runs comfortably	25–40 tok/s
NVIDIA GeForce RTX 5080 · 16GB VRAM	15B Q5_K_M	✅ Runs (tight)	35–55 tok/s
NVIDIA GeForce RTX 5090 · 32GB VRAM	15B Q8_0	✅ Runs comfortably	45–75 tok/s
AMD Radeon RX 7900 XTX · 24GB VRAM	15B Q8_0	✅ Runs comfortably	20–35 tok/s