AMD Instinct MI300X~923 tok/s (Q4)

context-labs/meta-llama-Llama-3.2-3B-Instruct-FP16 speed on AMD Instinct MI300X

Quantization-specific throughput and VRAM requirements for context-labs/meta-llama-Llama-3.2-3B-Instruct-FP16 running on AMD Instinct MI300X.

Speed Snapshot

Topline estimate from compatibility data

Modelcontext-labs/meta-llama-Llama-3.2-3B-Instruct-FP16

GPUAMD Instinct MI300X

Q4 speed923 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	192GB	923 tok/s	✅ Fits
Q8	3GB	192GB	639 tok/s	✅ Fits
FP16	6GB	192GB	347 tok/s	✅ Fits