Question 1

Can AMD Instinct MI350X 288GB run Qwen3.5 397B A17B?

Accepted Answer

Yes, AMD Instinct MI350X 288GB can run Qwen3.5 397B A17B with a D grade (Very compromised). Expected decode speed: 21.0 tok/s.

Question 2

How much VRAM does Qwen3.5 397B A17B need?

Accepted Answer

Qwen3.5 397B A17B (397B parameters) requires approximately 334.2 GB of memory with Q4_K_M quantization.

Question 3

What is the best quantization for Qwen3.5 397B A17B?

Accepted Answer

The recommended quantization for Qwen3.5 397B A17B is Q4_K_M, which balances quality and memory efficiency.

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	F	Too heavy	24.1 tok/s	11677 ms	23K
Chat	D	Runs with offload (needs ~12.1 GB host RAM)	23.1 tok/s	4574 ms	8K
Coding	D	Very compromised	21.0 tok/s	9607 ms	14K
RAG	F	Too heavy	24.1 tok/s	14597 ms	23K
Reasoning	D	Very compromised (needs ~33.5 GB host RAM)	21.3 tok/s	10751 ms

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	154.8 GB	Low	C41
Q3_K_S	3	194.5 GB	Low	C44
NVFP4Best for your GPU

Can AMD Instinct MI350X 288GB run Qwen3.5 397B A17B?

Memory breakdown