localai.computer

Loading content...

GPUs for AI Models: Benchmarks & Specs

Can Apple M2 Ultra run codellama/CodeLlama-34b-hf?

Runs Q4192GB VRAM availableRequires 17GB+

Apple M2 Ultra meets the minimum VRAM requirement for Q4 inference of codellama/CodeLlama-34b-hf. 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	17GB	192GB	40.89 tok/s	✅ Fits comfortably
Q8	35GB	192GB	28.13 tok/s	✅ Fits comfortably
FP16	70GB	192GB	13.93 tok/s	✅ Fits comfortably

Best current price

Apple M2 Ultra

$5,999.00 on Amazon

Suitable alternatives

AMD Instinct MI300X

192GB

278.02 tok/s

Price: —

NVIDIA H200 SXM 141GB

141GB

217.90 tok/s

Price: —

AMD Instinct MI300X

192GB

More questions

Apple M2 Ultra specs & pricing Full guide for codellama/CodeLlama-34b-hf