Can NVIDIA GeForce RTX 4090 run Qwen3 32B?

Yes, at Q5_K_M (23.4 GB) or lower. Higher quantizations like Q6_K (27.0 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.

What's the best quantization for Qwen3 32B?

For Qwen3 32B, Q4_K_M (19.8 GB) offers the best balance of quality and VRAM usage. Q5_0 (20.6 GB) provides better quality if you have the VRAM.

Can I run Qwen3 32B on a Mac?

Qwen3 32B requires at least 19.8 GB at Q4_K_M, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.

Can I run Qwen3 32B locally?

Yes — Qwen3 32B can run locally on consumer hardware. At Q4_K_M quantization it needs 19.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is Qwen3 32B?

At Q4_K_M, Qwen3 32B can reach ~147 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~33 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

What's the download size of Qwen3 32B?

At Q4_K_M, the download is about 19.20 GB. The full-precision Q8_0 version is 32.00 GB.

Alibaba·Qwen·Qwen3ForCausalLM

Qwen3 32B — Hardware Requirements & GPU Compatibility

Chat

Qwen3 32B is the flagship dense model in Alibaba Cloud's Qwen 3 series, with 32 billion parameters. It is instruction-tuned for chat and delivers strong performance across reasoning, coding, mathematics, and multilingual tasks. Qwen3 32B supports a hybrid thinking mode that allows the model to engage in extended chain-of-thought reasoning or respond quickly depending on the task, giving users flexibility between depth and speed. The model requires a GPU with at least 24GB of VRAM for quantized inference, placing it within reach of high-end consumer cards like the RTX 4090. It represents a significant generational improvement over Qwen 2.5 in both instruction following and knowledge breadth. Released under the Apache 2.0 license.

5.0M downloads 668 likesJul 202541K context

Specifications

Publisher: Alibaba
Family: Qwen
Parameters: 32B
Architecture: Qwen3ForCausalLM
Context Length: 40,960 tokens
Vocabulary Size: 151,936
Release Date: 2025-07-26
License: Apache 2.0

Get Started

HuggingFace

Qwen/Qwen3-32B

How Much VRAM Does Qwen3 32B Need?

Select a quantization to see compatible GPUs below.

Quantization	Bits	VRAM	+ Context	File Size	Quality
Q4_K_M	4.80	19.8 GB	26.2 GB	19.20 GB	4-bit medium quantization — most popular sweet spot
Q5_0	5.00	20.6 GB	27.0 GB	20.00 GB	5-bit legacy quantization
Q5_K_M	5.70	23.4 GB	29.8 GB	22.80 GB	5-bit medium quantization — good quality/size tradeoff
Q6_K	6.60	27.0 GB	33.4 GB	26.40 GB	6-bit quantization, very good quality
Q8_0	8.00	32.6 GB	39.0 GB	32.00 GB	8-bit quantization, near-lossless

Which GPUs Can Run Qwen3 32B?

Q4_K_M · 19.8 GB

Show professional

Qwen3 32B (Q4_K_M) requires 19.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 26+ GB is recommended. Using the full 41K context window can add up to 6.4 GB, bringing total usage to 26.2 GB. 6 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.

Runs great

— Plenty of headroom

NVIDIA GeForce RTX 5090~59 tok/s

Decent

— Enough VRAM, may be tight

NVIDIA GeForce RTX 3090 Ti~33 tok/s NVIDIA GeForce RTX 4090~33 tok/s NVIDIA GeForce RTX 3090~31 tok/s AMD Radeon RX 7900 XTX~27 tok/s AMD Radeon RX 7900 XT~22 tok/s

Which Devices Can Run Qwen3 32B?

Q4_K_M · 19.8 GB

21 devices with unified memory can run Qwen3 32B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Mini M4 Pro (24 GB).

Related Models

Derivatives (7)

Foresight 32B Goedel Prover v2 32B Qwen3 32B AWQ Qwen3 32B GGUF Qwen3 32B MLX 4bit Qwen3 32B NVFP4 T Pro IT 2.1

Frequently Asked Questions

How much VRAM does Qwen3 32B need?: Qwen3 32B requires 19.8 GB of VRAM at Q4_K_M, or 32.6 GB at Q8_0. Full 41K context adds up to 6.4 GB (26.2 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 32B × 4.8 bits ÷ 8 = 19.2 GB
KV Cache + Overhead ≈ 0.6 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 7 GB (at full 41K context)
VRAM usage by quantization
Q4_K_M
19.8 GB
Q4_K_M + full context
26.2 GB
Learn more about VRAM estimation →
Can NVIDIA GeForce RTX 4090 run Qwen3 32B?: Yes, at Q5_K_M (23.4 GB) or lower. Higher quantizations like Q6_K (27.0 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
What's the best quantization for Qwen3 32B?: For Qwen3 32B, Q4_K_M (19.8 GB) offers the best balance of quality and VRAM usage. Q5_0 (20.6 GB) provides better quality if you have the VRAM.
VRAM requirement by quantization
Q4_K_M ★
19.8 GB~89%
Q5_0
20.6 GB~90%
Q5_K_M
23.4 GB~92%
Q6_K
27.0 GB~95%
Q8_0
32.6 GB~99%
★ Recommended — best balance of quality and VRAM usage.
Learn more about quantization →
Can I run Qwen3 32B on a Mac?: Qwen3 32B requires at least 19.8 GB at Q4_K_M, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
Can I run Qwen3 32B locally?: Yes — Qwen3 32B can run locally on consumer hardware. At Q4_K_M quantization it needs 19.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3 32B?: At Q4_K_M, Qwen3 32B can reach ~147 tok/s on AMD Instinct MI300X. On NVIDIA GeForce RTX 4090: ~33 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: AMD Instinct MI300X → 5300 ÷ 19.8 × 0.55 = ~147 tok/s
Estimated speed at Q4_K_M (19.8 GB)
AMD Instinct MI300X
~147 tok/s
NVIDIA GeForce RTX 4090
~33 tok/s
NVIDIA H100 SXM
~110 tok/s
AMD Instinct MI250X
~91 tok/s
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
Learn more about tok/s estimation →
What's the download size of Qwen3 32B?: At Q4_K_M, the download is about 19.20 GB. The full-precision Q8_0 version is 32.00 GB.