Question 1

Can Radeon PRO W7600 8GB run Llama 3.2 3B Instruct?

Accepted Answer

Yes, Radeon PRO W7600 8GB can run Llama 3.2 3B Instruct with a B grade (Runs well). Expected decode speed: 97.9 tok/s.

Question 2

How much VRAM does Llama 3.2 3B Instruct need?

Accepted Answer

Llama 3.2 3B Instruct (3B parameters) requires approximately 5.0 GB of memory with Q5_K_M quantization.

Question 3

What is the best quantization for Llama 3.2 3B Instruct?

Accepted Answer

The recommended quantization for Llama 3.2 3B Instruct is Q5_K_M, which balances quality and memory efficiency.

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	B	Runs well	97.9 tok/s	2876 ms	50K
Chat	B	Runs well	97.9 tok/s	1078 ms	13K
Coding	B	Runs well	97.9 tok/s	1977 ms	26K
RAG	B	Runs well	97.9 tok/s	3595 ms	50K
Reasoning	B	Runs well	97.9 tok/s	2337 ms	26K

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	1.2 GB	Low	D33
Q3_K_S	3	1.5 GB	Low	D34
NVFP4	4

Can Radeon PRO W7600 8GB run Llama 3.2 3B Instruct?

Memory breakdown