Qwen 3 72B is Alibaba's April 2025 flagship dense release and the first major open model to ship a hybrid thinking mode — one set of weights, two behaviors. Set enable_thinking=true for o1-style chain-of-thought on math and code, or false for fast direct answers. It tops Qwen 2.5 72B on AIME, LiveCodeBench, and BFCL while inheriting Qwen's strong multilingual coverage (119 languages). Apache 2.0 license, identical VRAM footprint to Qwen 2.5 72B. At Q4_K_M it fits across 2x RTX 4090 (48 GB) or 1x H100 80 GB. The reasoning mode roughly doubles output tokens, so plan KV-cache headroom accordingly. See [Q4_K_M quantization](/glossary/q4-k-m) for the math.
Qwen 3 72B needs at minimum 43.6 GB of VRAM at Q4_K_M quantization (158.4 GB at FP16). The cheapest GPU that comfortably fits with KV-cache headroom is the Apple Mac mini (M4 Pro, 64 GB) (64 GB VRAM, $2,199 MSRP). Community benchmark submissions are open. This model fits a single consumer GPU under 48 GB, so a one-card build works.
Weights only. Add ~20-30% for KV cache at typical context lengths.
| Quant | VRAM | Quality | Notes |
|---|---|---|---|
| FP16 | 158.4 GB | Reference | Training-precision weights |
| Q8_0 | 79.2 GB | Near-lossless | 8-bit, ~0.1% perplexity hit |
| Q6_K | 64.2 GB | Very high | 6-bit, near Q8 quality |
| Q5_K_M | 54.6 GB | High | Strong middle ground |
| Q4_K_M | 43.6 GB | Balanced (recommended) | Default for local deployments |
| Q4_0 | 44.6 GB | Legacy 4-bit | Older GGUF, kept for compatibility |
| Q3_K_M | 34.1 GB | Lossy | When VRAM is very tight |
| Q2_K | 25.3 GB | Extreme | Rescue option, quality degrades visibly |
Filtered from MyAIHardware's GPU database. FP16 needs 158.4 GB; Q4_K_M needs 43.6 GB.
We don't have community benchmarks for this exact model yet.
Official weights + popular runtime tags.
ollama pull qwen3:72blms get Qwen/Qwen3-72B-GGUFStep-by-step guides that use this model.
Models in a similar size or capability class.
Use these in papers, blog posts, or internal docs.
@misc{qwen-3-72b-2025,
title={Qwen 3 72B},
author={Alibaba Cloud Qwen Team},
year={2025},
url={https://huggingface.co/Qwen/Qwen3-72B}
}Alibaba Cloud Qwen Team (2025). Qwen 3 72B [Model card]. Hugging Face. https://huggingface.co/Qwen/Qwen3-72B
Qwen 3 72B (Qwen 3, Alibaba Cloud Qwen Team, 2025). Available at https://huggingface.co/Qwen/Qwen3-72B.