localai.computer

Loading content...

GPUs for AI Models: Benchmarks & Specs

Can Apple M4 Max run NousResearch/Hermes-3-Llama-3.1-70B?

Runs Q4128GB VRAM availableRequires 34GB+

Apple M4 Max meets the minimum VRAM requirement for Q4 inference of NousResearch/Hermes-3-Llama-3.1-70B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.

Quantization breakdown

Quantization	VRAM needed	VRAM available	Estimated speed	Verdict
Q4	34GB	128GB	14.88 tok/s	✅ Fits comfortably
Q8	69GB	128GB	9.75 tok/s	✅ Fits comfortably
FP16	138GB	128GB	5.18 tok/s	❌ Not recommended

Suitable alternatives

AMD Instinct MI300X

192GB

142.20 tok/s

Price: —

NVIDIA H200 SXM 141GB

141GB

138.60 tok/s

Price: —

AMD Instinct MI300X

192GB

More questions

Apple M4 Max specs & pricing Full guide for NousResearch/Hermes-3-Llama-3.1-70B