Qwen3 32B (Q3_K_S) — 15.4 GBon Apple M2 Pro 16GB

Q3_K_S Apple M2 Pro 16GB

Overview

Qwen3 32B is a 32B parameter dense language model by Qwen, with code, multilingual, thinking, tool-calls capabilities. It supports a context window of up to 40,960 tokens.

Qwen3 32B is a 32-billion-parameter dense transformer from Alibaba's Qwen team, combining thinking capabilities with strong code generation, tool calling, and multilingual support. It occupies a mid-range parameter class that balances reasoning depth with practical deployment requirements, outperforming many larger models on math and logic benchmarks. The model supports 14 languages including English, Chinese, and Arabic. With a 40K context window and flash attention, it fits on a single high-end GPU at Q4 quantization for self-hosted inference.

At Q3_K_S quantization (low quality tier), the model weighs 13.4 GB. This fits within the 16 GB of VRAM on Apple M2 Pro 16GB, enabling full GPU inference.

Hardware Requirements

Model size	13.4 GB
VRAM available	16 GB
VRAM used	15.4 GB
GPU layers	64 / 64
Context size	4,949
Backend	metal
Flash attention	Yes

Performance Notes

Shorter conversations

Context size has been reduced due to memory constraints. This may affect the model's ability to handle long conversations.

Deploy

Install llama.cpp

brew install llama.cpp

Download Model

curl -L -o qwen3-32b.gguf "https://huggingface.co/unsloth/Qwen3-32B-GGUF/resolve/main/Qwen3-32B-Q3_K_S.gguf"

Start Server

llama-server \
  -m qwen3-32b.gguf \
  --n-gpu-layers 64 \
  --ctx-size 4949 \
  --flash-attn

Verify

curl http://localhost:8080/health

Explore

• Configure a deployment
• Browse models
• Browse hardware

Other quantizations

• Qwen3 32B (Q8_0)
• Qwen3 32B (Q5_K_M)
• Qwen3 32B (Q4_K_M)

Other hardware

• Qwen3 32B on CPU Only
• Qwen3 32B on NVIDIA A100 80GB
• Qwen3 32B on NVIDIA H100

Frequently Asked Questions

How much VRAM does Qwen3 32B (Q3_K_S) need?

The Q3_K_S quantization of Qwen3 32B requires 13.4 GB. All 64 layers fit in the 16 GB of VRAM available on Apple M2 Pro 16GB, enabling full GPU acceleration.

Can I run Qwen3 32B on Apple M2 Pro 16GB?

Yes. Apple M2 Pro 16GB provides 16 GB of VRAM, which is enough to run Qwen3 32B (Q3_K_S) with all layers on the GPU for optimal performance.

What is quantization?

Quantization reduces a model's numerical precision from its original floating-point format to a more compact representation. This shrinks the file size and VRAM footprint, making it possible to run large models on consumer hardware. The trade-off is a small reduction in output quality. Q3_K_S compresses Qwen3 32B from its original size down to 13.4 GB.

What quantization should I choose for Qwen3 32B?

Q3_K_S is a low-quality quantization. Higher-quality quants (Q8, Q6) preserve more model accuracy but need more VRAM. Lower quants (Q4, Q3, Q2) reduce VRAM usage at the cost of some quality. Choose based on your available hardware and quality requirements.

What is flash attention and why is it enabled?

Flash attention is a memory-efficient algorithm that speeds up the attention mechanism in transformer models. It reduces VRAM usage during inference by avoiding the materialisation of the full attention matrix. For Qwen3 32B on Apple M2 Pro 16GB, flash attention is enabled to maximise context length and throughput within the available 16 GB of VRAM.

How do I run Qwen3 32B (Q3_K_S) with Ollama?

Run ollama run qwen3:32b-q3_k_s to start Qwen3 32B (Q3_K_S). Ollama handles downloading the model weights automatically on first run.

Last updated: March 5, 2026