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

Qwen3.5 35B A3B (35B parameters) requires approximately 34.4 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, NVIDIA A16 64GB can run Qwen3.5 35B A3B with a C grade (Runs well). Expected decode speed: 21.9 tok/s.

CUsable

Runs well

Using Q4_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

21.9 tok/s

TTFT

8832 ms

Safe context

30K

Memory

34.4 GB / 64.0 GB

Weights21.3 GB

KV Cache5.5 GB

Runtime1.2 GB

Headroom6.4 GB

Workload	Grade	Fit	Decode	TTFT	Context
Agentic Coding	C	Runs well	20.2 tok/s	13917 ms	51K
Chat	C	Runs well	21.9 tok/s	4817 ms	16K
Coding	C	Runs well	21.9 tok/s	8832 ms	30K
RAG	C	Runs well	21.9 tok/s	16058 ms	51K
Reasoning	C	Runs well	21.9 tok/s	10438 ms	30K

How Qwen3.5 35B A3B (35B params) fits at each quantization level on NVIDIA A16 64GB (64.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	D34
Q3_K_S	3	17.2 GB	Low	D35
NVFP4	4

HuggingFace

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

Upgrade options

NVIDIA A100 80GBBudget pick

C80.2 tok/s decode

~$15,000 MSRP

NVIDIA H100 PCIe 80GBBest value

C78.7 tok/s decode

~$30,000 MSRP

NVIDIA H100 80GBBiggest leap

C131.8 tok/s decode

~$40,000 MSRP

NVIDIA H800 80GBNVIDIA upgrade

C113.8 tok/s decode