Question 1

Can NVIDIA H800 80GB run Llama 3.3 70B Instruct?

Accepted Answer

Yes, NVIDIA H800 80GB can run Llama 3.3 70B Instruct with a B grade (Runs well). Expected decode speed: 50.6 tok/s.

Question 2

How much VRAM does Llama 3.3 70B Instruct need?

Accepted Answer

Llama 3.3 70B Instruct (70B parameters) requires approximately 62.8 GB of memory with Q4_K_M quantization.

Question 3

What is the best quantization for Llama 3.3 70B Instruct?

Accepted Answer

The recommended quantization for Llama 3.3 70B Instruct is Q4_K_M, which balances quality and memory efficiency.

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	C	Tight fit	56.9 tok/s	4948 ms	35K
Chat	B	Runs well	56.9 tok/s	1856 ms	11K
Coding	B	Runs well	50.6 tok/s	3827 ms	20K
RAG	C	Tight fit	56.9 tok/s	6185 ms	35K
Reasoning	B	Runs well	56.9 tok/s	4020 ms	20K

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	27.3 GB	Low	D37
Q3_K_S	3	34.3 GB	Low	D38
NVFP4	4

Can NVIDIA H800 80GB run Llama 3.3 70B Instruct?

Memory breakdown