AMD Instinct MI300X~279 tok/s (Q4)

meta-llama/Llama-3.3-70B-Instruct speed on AMD Instinct MI300X

Quantization-specific throughput and VRAM requirements for meta-llama/Llama-3.3-70B-Instruct running on AMD Instinct MI300X.

Speed Snapshot

Topline estimate from compatibility data

Modelmeta-llama/Llama-3.3-70B-Instruct

GPUAMD Instinct MI300X

Q4 speed279 tok/s

Q4 VRAM required34GB

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	34GB	192GB	279 tok/s	✅ Fits
Q8	68GB	192GB	190 tok/s	✅ Fits
FP16	137GB	192GB	108 tok/s	✅ Fits