NVIDIA A100 80GB SXM4~104 tok/s (Q4)

dphn/dolphin-2.9.1-yi-1.5-34b speed on NVIDIA A100 80GB SXM4

Quantization-specific throughput and VRAM requirements for dphn/dolphin-2.9.1-yi-1.5-34b running on NVIDIA A100 80GB SXM4.

Speed Snapshot

Topline estimate from compatibility data

Modeldphn/dolphin-2.9.1-yi-1.5-34b

GPUNVIDIA A100 80GB SXM4

Q4 speed104 tok/s

Q4 VRAM required17GB

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	17GB	80GB	104 tok/s	✅ Fits
Q8	35GB	80GB	79 tok/s	✅ Fits
FP16	70GB	80GB	36 tok/s	✅ Fits