Apple M2 Max~17 tok/s (Q4)

codellama/CodeLlama-34b-hf speed on Apple M2 Max

Quantization-specific throughput and VRAM requirements for codellama/CodeLlama-34b-hf running on Apple M2 Max.

Speed Snapshot

Topline estimate from compatibility data

Modelcodellama/CodeLlama-34b-hf

GPUApple M2 Max

Q4 speed17 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	96GB	17 tok/s	✅ Fits
Q8	35GB	96GB	13 tok/s	✅ Fits
FP16	70GB	96GB	8 tok/s	✅ Fits