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

Qwen3.5 35B A3B (35B parameters) requires approximately 33.2 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, MacBook Pro M3 Max 48GB can run Qwen3.5 35B A3B with a C grade (Runs with offload). Expected decode speed: 12.2 tok/s.

CUsable

Runs with offload

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs with offload

Decode

12.2 tok/s

TTFT

15898 ms

Safe context

17K

Memory

33.2 GB / 34.6 GB

Weights21.4 GB

KV Cache5.5 GB

Runtime1.2 GB

Headroom5.2 GB

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	D	Very compromised (needs ~2.3 GB host RAM)	10.9 tok/s	25876 ms	29K
Chat	C	Tight fit	11.2 tok/s	9394 ms	9K
Coding	C	Runs with offload	12.2 tok/s	15898 ms	17K
RAG	D	Very compromised (needs ~2.3 GB host RAM)	10.9 tok/s	32345 ms	29K
Reasoning	C	Runs with offload	11.2 tok/s	20354 ms

How Qwen3.5 35B A3B (35B params) fits at each quantization level on MacBook Pro M3 Max 48GB (34.6 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	D38
Q3_K_S	3	17.2 GB	Low	C40
NVFP4	4

HuggingFace

huggingface-cli download hf-unsloth--qwen3-5-35b-a3b-gguf

Upgrade options

Mac mini M4 64GBBudget pick

C4 tok/s decode

~$1,099 MSRP

MacBook Pro M4 Pro 64GBBest value

C9.8 tok/s decode

~$1,599 MSRP