How much VRAM does Qwen3.5 35B A3B need?

Qwen3.5 35B A3B (35B parameters) requires approximately 31.2 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen3.5 35B A3B?

The recommended quantization for Qwen3.5 35B A3B is Q4_K_M, which balances quality and memory efficiency.

Can it run?

Yes, AMD Instinct MI60 32GB can run Qwen3.5 35B A3B with a C grade (Runs with offload). Expected decode speed: 23.5 tok/s.

CUsable

Runs with offload

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs with offload

Decode

23.5 tok/s

TTFT

8238 ms

Safe context

16K

Memory

31.2 GB / 32.0 GB

Weights21.3 GB

KV Cache5.5 GB

Runtime1.2 GB

Headroom3.2 GB

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	D	Very compromised (needs ~2.7 GB host RAM)	20.9 tok/s	13442 ms	28K
Chat	C	Tight fit	23.5 tok/s	4493 ms	9K
Coding	C	Runs with offload	23.5 tok/s	8238 ms	16K
RAG	D	Very compromised (needs ~2.7 GB host RAM)	20.9 tok/s	16802 ms	28K
Reasoning	C	Runs with offload	23.5 tok/s	9735 ms

How Qwen3.5 35B A3B (35B params) fits at each quantization level on AMD Instinct MI60 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	D39
Q3_K_S	3	17.2 GB	Low	C41
NVFP4	4

HuggingFace

huggingface-cli download hf-lmstudio-community--qwen3-5-35b-a3b-gguf

Upgrade options

MacBook Pro M4 Pro 64GBBudget pick

C9.8 tok/s decode

~$1,599 MSRP

MacBook Pro M3 Max 64GBBest value

C11.2 tok/s decode

~$2,499 MSRP

NVIDIA A100 40GBBiggest leap