Question 1

Can RX 6750 XT 12GB run Qwen2.5 1.5B Instruct?

Accepted Answer

Yes, RX 6750 XT 12GB can run Qwen2.5 1.5B Instruct with a C grade (Runs well). Expected decode speed: 311.0 tok/s.

Question 2

How much VRAM does Qwen2.5 1.5B Instruct need?

Accepted Answer

Qwen2.5 1.5B Instruct (1.5B parameters) requires approximately 4.1 GB of memory with Q4_K_M quantization.

Question 3

What is the best quantization for Qwen2.5 1.5B Instruct?

Accepted Answer

The recommended quantization for Qwen2.5 1.5B Instruct is Q4_K_M, which balances quality and memory efficiency.

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	C	Runs well	229.0 tok/s	1230 ms	93K
Chat	C	Runs well	229.0 tok/s	461 ms	23K
Coding	C	Runs well	311.0 tok/s	622 ms	47K
RAG	C	Runs well	229.0 tok/s	1537 ms	93K
Reasoning	C	Runs well	229.0 tok/s	999 ms	47K

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	0.6 GB	Low	D31
Q3_K_S	3	0.7 GB	Low	D31
NVFP4	4

Can RX 6750 XT 12GB run Qwen2.5 1.5B Instruct?

Memory breakdown