AMD Instinct MI300X~286 tok/s (Q4)

codellama/CodeLlama-34b-hf speed on AMD Instinct MI300X

Quantization-specific throughput and VRAM requirements for codellama/CodeLlama-34b-hf running on AMD Instinct MI300X.

Speed Snapshot

Topline estimate from compatibility data

Modelcodellama/CodeLlama-34b-hf

GPUAMD Instinct MI300X

Q4 speed286 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	192GB	286 tok/s	✅ Fits
Q8	35GB	192GB	184 tok/s	✅ Fits
FP16	70GB	192GB	101 tok/s	✅ Fits