Alibaba

Qwen 3.5 35B A3B

Name: Qwen 3.5 35B A3B
Rating: 89 (87 reviews)
Author: Alibaba

Frontier

Jun 2025Released131K tokensContextApache 2.0License97 ExceptionalQuality

Qwen 3.5 35B A3B (35B parameters) requires approximately 24.6 GB of VRAM with Q4_K_M quantization. As a Mixture of Experts model with 3B active parameters, it uses less memory than its total parameter count suggests. For the best balance of quality and speed, we recommend hardware with at least 29 GB of VRAM.

Get started

— copy & paste to run locally

Copy-paste commands to run Qwen 3.5 35B A3B on your machine.

Run

ollama run qwen3.5:35b-a3b

Quick specs

Parameters35B (3B active)

Architecturemoe (MoE)

Context131K tokens

Modalitytext

Min RAM13.7 GB

Rec. RAM21.3 GB (Q4_K_M)

LicenseApache 2.0

FamilyQwen

✓ Code✓ Chat

About this model

Qwen3.5 35B A3B is a Mixture-of-Experts model with only 3B active parameters per token, offering surprisingly strong performance at very low inference cost.

•MoE architecture: 35B total params but only 3B active — fast and memory-efficient
•Quality comparable to dense 7-8B models at a fraction of the compute
•Runs well on 8 GB VRAM GPUs at Q4_K_M

Related models

Quick picks

Best budgetS

Mac mini M4 64GB~$1,099 — 17 tok/s

Best overallS

NVIDIA A100 40GB~$10,000 — 181 tok/s

Best hardware

Top picks for Qwen 3.5 35B A3B

NVIDIA A100 40GBS

40 GB

Mac Studio M2 Ultra 64GBS

64 GB

Mac Studio M1 Ultra 64GBS

64 GB

MacBook Pro M4 Max 64GBS

64 GB

RTX 6000 Ada 48GBS

48 GB

Run this model

Qwen 3.5 35B A3B on NVIDIA A100 40GB Qwen 3.5 35B A3B on Mac Studio M2 Ultra 64GB Qwen 3.5 35B A3B on Mac Studio M1 Ultra 64GB

Quantization options

VRAM estimates by quant level

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	—
Q3_K_S	3	17.2 GB	Low	—
NVFP4	4	19.6 GB	Medium	—
Q4_K_M	4	21.3 GB	Medium	—
Q5_K_M	5	25.2 GB	High	—
Q6_K	6	28.7 GB	High	—
Q8_0	8	37.5 GB	Very High	—
F16	16	71.8 GB	Maximum	—

Quality benchmarks

Qwen 3.5 35B A3B benchmark scores

Benchmark verified

Coding

SWE-bench Verified69.2%

HumanEval+—

Aider Polyglot—

LiveCodeBench74.6%

Reasoning

MMLU-Pro85.3%

GPQA Diamond84.2%

MATH-500—

ARC Challenge—

General

Chatbot Arena—

IFEval91.9%

Source: official · 2026-03-01

Hardware compatibility

Fit estimates across all hardware

Open calculator

Computing compatibility...

Memory breakdown

Reference: RTX 2060 6GB

Weights21.3 GB

KV Cache1.5 GB

Runtime1.2 GB

Headroom0.6 GB

Frequently asked questions

FAQ — Qwen 3.5 35B A3B

How much VRAM does Qwen 3.5 35B A3B need?

Qwen 3.5 35B A3B (35B parameters) requires approximately 24.6 GB of VRAM with Q4_K_M quantization. Lower quantizations like Q4_K_M use less memory but may reduce quality.

Can I run Qwen 3.5 35B A3B on a Mac mini M4 64GB?

Yes, Mac mini M4 64GB can run Qwen 3.5 35B A3B with a compatibility score of 92/100. It provides 64 GB of memory and achieves approximately 17.1 tokens per second.

What is the best quantization for Qwen 3.5 35B A3B?

The recommended quantization for Qwen 3.5 35B A3B is Q4_K_M, which offers the best balance between model quality and memory efficiency. Higher quantizations preserve more quality but require more VRAM.

What hardware is recommended for Qwen 3.5 35B A3B?

The top recommended hardware for Qwen 3.5 35B A3B: NVIDIA A100 40GB (score: 98/100), Mac Studio M2 Ultra 64GB (score: 97/100), Mac Studio M1 Ultra 64GB (score: 97/100). These provide the best combination of memory, bandwidth, and compute for running this model locally.

Is Qwen 3.5 35B A3B good for chat?

Yes, Qwen 3.5 35B A3B is well-suited for chat as well as coding, general. It was designed with these use cases in mind.