Apple M2 Ultra~20 tok/s (Q4)

NousResearch/Hermes-3-Llama-3.1-70B speed on Apple M2 Ultra

Quantization-specific throughput and VRAM requirements for NousResearch/Hermes-3-Llama-3.1-70B running on Apple M2 Ultra.

Speed Snapshot

Topline estimate from compatibility data

ModelNousResearch/Hermes-3-Llama-3.1-70B

GPUApple M2 Ultra

Q4 speed20 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	20 tok/s	✅ Fits
Q8	69GB	192GB	16 tok/s	✅ Fits
FP16	138GB	192GB	9 tok/s	✅ Fits