NVIDIA A100 80GB SXM4~324 tok/s (Q4)

bigcode/starcoder2-3b speed on NVIDIA A100 80GB SXM4

Quantization-specific throughput and VRAM requirements for bigcode/starcoder2-3b running on NVIDIA A100 80GB SXM4.

Speed Snapshot

Topline estimate from compatibility data

Modelbigcode/starcoder2-3b

GPUNVIDIA A100 80GB SXM4

Q4 speed324 tok/s

Q4 VRAM required2GB

Data Source

Calculation and benchmark status

Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.

For full verdict logic and alternate GPUs, see the canonical compatibility page.

Quantization Speed Table

Quantization	VRAM needed	VRAM available	Speed	Verdict
Q4	2GB	80GB	324 tok/s	✅ Fits
Q8	3GB	80GB	263 tok/s	✅ Fits
FP16	6GB	80GB	132 tok/s	✅ Fits