Qwen3 32B — Hardware Requirements & GPU Compatibility
Chat
Qwen3 32B is a 32B-parameter open language model from openwalrus in the Qwen 3 family. It supports a context window of up to 40,960 tokens. At Q4_K_M it needs about 19.84 GB of VRAM — see which GPUs and Macs can run it below.
Decent on a 24 GB GPU
Runs from 12 GB (IQ2_XXS · 16K)Best on 24 GB (Q4_K_M · ~33 tok/s · 16K)Macs from 16 GB (IQ2_XXS · ~15 tok/s)
Apache 2.0
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run Qwen3 32B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve openwalrus/Qwen3-32B --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 5090 (32 GB) (9 GB headroom) · Q4_K_M
- Generation speed
- ~59 tok/s
- generation speed
- Cost per 1M output tokens
- $2.35
- per 1M output tokens
How Much VRAM Does Qwen3 32B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 14.2 GB | 19.3 GB | 2-bit · K-quant — 2-bit quantization with K-quant improvements | Fits: 40K context · ~46 tok/s | |
| 14.6 GB | 19.7 GB | 3-bit small — 3-bit small quantization | Fits: 40K context · ~45 tok/s | |
| 16.2 GB | 21.3 GB | 3-bit medium — 3-bit medium quantization | Fits: 40K context · ~40 tok/s | |
| 16.6 GB | 21.7 GB | 4-bit · legacy — 4-bit legacy quantization | Fits: 40K context · ~39 tok/s | |
| 19.8 GB | 24.9 GB | 4-bit medium — 4-bit medium quantization — most popular sweet spot | Fits: 16K context · ~33 tok/s | |
| 23.4 GB | 28.5 GB | 5-bit medium — 5-bit medium quantization — good quality/size tradeoff | Fits: 4K context · ~28 tok/s | |
| 27.0 GB | 32.1 GB | 6-bit, very good — 6-bit quantization, very good quality | Does not fit: needs 29.4 GB | |
| 32.6 GB | 37.7 GB | 8-bit, near-lossless — 8-bit quantization, near-lossless | Does not fit: needs 35 GB |
Selected Q4_K_M
4-bit medium quantization22.2GBat 16K context
- Weights
- 19.2 GB
- KV cache
- 2.7 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 1.8 GB free · ~33 tok/s
≥50 tok/s needs ≥1.52 TB/s · RTX 5090 ~59
Which Hardware Can Run Qwen3 32B?
Q4_K_M · 19.8 GBQwen3 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. 8 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti. 122 devices with unified memory can run Qwen3 32B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Studio M1 Max (32 GB).
20 GB
tight · up to 2K ctx
1 GPU
RX 7900 XT~24Simulate output on RX 7900 XT32–40 GB
fits · 9.8 GB free · up to 40K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~59Simulate output on RTX 5090M5 Max36 GB~16Simulate output on Mac Studio M5 Max (36 GB)M532 GB~5Simulate output on MacBook Air 13" M5 (32 GB)Orin~7Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~4Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at Q4_K_M
Alternatives to Qwen3 32B
Qwen 3 family · 79 models →Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Nanbeige4.3 33BNanbeige | — | 23.7 GB | ~32 | same size |
| Hy Memory 30B A3BTencent | — | 19.1 GB | ~184 | same size |
| Granite Switch 4.1 30BIBM | — | 22.7 GB | ~35 | same size |
| Llm Jp 4.1 32B A3b Thinkingllm-jp | — | 20.1 GB | ~188 | same size |
| Llm Jp 4.1 33B Thinkingllm-jp | — | 22.5 GB | ~35 | same size |
| Agnes 3.0 FlashAgnes-AI | — | 22.1 GB | ~35 | same size |
Specifications
- Publisher
- openwalrus
- Family
- Qwen 3
- Parameters
- 32B
- Architecture
- Qwen3ForCausalLM
- Context Length
- 40,960 tokens
- Vocabulary Size
- 151,936
- Release Date
- 2026-03-10
- License
- Apache 2.0
Frequently Asked Questions
How much VRAM does Qwen3 32B need?
Qwen3 32B requires 19.8 GB of VRAM at Q4_K_M, or 64.6 GB at BF16. 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)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 7 GB (at full 41K context)
VRAM usage by quantization
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_K_S (22.6 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 9.4 GB.
VRAM requirement by quantization
★ Recommended — best balance of quality and VRAM usage.
Can I run Qwen3 32B on a Mac?
Yes — Mac Mini M2 Pro (16 GB) and 133 other Macs can run Qwen3 32B, the smallest at IQ2_XXS. Apple Silicon uses unified memory, so the model shares RAM with the system. At Q4_K_M you need at least 19.8 GB of usable unified memory (RAM minus macOS overhead), from Mac Mini M5 Pro (24 GB).
Can I run Qwen3 32B locally?
Yes — Qwen3 32B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is Qwen3 32B?
At Q4_K_M, Qwen3 32B can reach ~242 tok/s on AMD Instinct MI350X. 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: NVIDIA B200 → 8000 ÷ 19.84 × 0.65 = ~262 tok/s
Estimated speed at Q4_K_M (19.8 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of Qwen3 32B?
At Q4_K_M, the download is about 19.20 GB. The full-precision BF16 version is 64.00 GB. The smallest option (IQ2_XXS) is 8.80 GB.
Which GPUs can run Qwen3 32B?
8 consumer GPUs can run Qwen3 32B at Q4_K_M. Top options include NVIDIA GeForce RTX 5090, AMD Radeon RX 7900 XT, AMD Radeon RX 7900 XTX. 1 GPU has plenty of headroom for comfortable inference.
Which devices can run Qwen3 32B?
122 devices with unified memory can run Qwen3 32B at Q4_K_M (19.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.