Qwen2.5 72B — Hardware Requirements & GPU Compatibility
Chat
Qwen2.5-72B is the base, pretrained 72.7-billion-parameter language model from Alibaba's Qwen2.5 series — it is not instruction-tuned and is not intended for direct conversational use; Alibaba recommends applying SFT, RLHF, or further pretraining on top of it. It uses a Transformer architecture with RoPE, SwiGLU, RMSNorm, QKV attention bias, 80 layers, and grouped-query attention (64 query heads, 8 key/value heads), with stronger coding, math, and structured-output ability than the earlier Qwen2 line, plus multilingual coverage across 29-plus languages. At 72.7 billion parameters, it needs a multi-GPU workstation to run at full precision, though quantized versions fit fewer cards. Context length is 131,072 tokens. It is released under Alibaba's custom Qwen license, which permits research and commercial use but requires a separate license from Alibaba once a product or service passes 100 million monthly active users. It was published in September 2024.
50.3K downloads
104 likesSpecifications
- Publisher
- Alibaba
- Family
- Qwen 2.5
- Parameters
- 72.7B
- Architecture
- Qwen2ForCausalLM
- Context Length
- 131,072 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2024-09-15
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Qwen2.5 72B Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 31.9 GB | 74.2 GB | 30.90 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 32.8 GB | 75.1 GB | 31.81 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 36.4 GB | 78.7 GB | 35.44 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 37.3 GB | 79.6 GB | 36.35 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 44.6 GB | 86.9 GB | 43.62 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_Mest. | 5.70 | 52.8 GB | 95.0 GB | 51.80 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_Kest. | 6.60 | 61.0 GB | 103.2 GB | 59.98 GB | 6-bit quantization, very good quality |
| Q8_0est. | 8.00 | 73.7 GB | 116.0 GB | 72.71 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Qwen2.5 72B?
Q4_K_M · 44.6 GBQwen2.5 72B (Q4_K_M) requires 44.6 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 58+ GB is recommended. Using the full 131K context window can add up to 42.3 GB, bringing total usage to 86.9 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Qwen2.5 72B?
Q4_K_M · 44.6 GB26 devices with unified memory can run Qwen2.5 72B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).
Runs great
— Plenty of headroom
Where to Download Qwen2.5 72B
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Benchmarks
Benchmark details →Related Models
Frequently Asked Questions
- How much VRAM does Qwen2.5 72B need?
Qwen2.5 72B requires 44.6 GB of VRAM at Q4_K_M, or 146.4 GB at BF16. Full 131K context adds up to 42.3 GB (86.9 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 72.7B × 4.8 bits ÷ 8 = 43.6 GB
KV Cache + Overhead ≈ 1 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 43.3 GB (at full 131K context)
VRAM usage by quantization
Q4_K_M44.6 GBQ4_K_M + full context86.9 GB- Can NVIDIA GeForce RTX 5090 run Qwen2.5 72B?
Yes, at Q2_K (31.9 GB) or lower. Higher quantizations like Q3_K_S (32.8 GB) exceed the NVIDIA GeForce RTX 5090's 32 GB.
- What's the best quantization for Qwen2.5 72B?
For Qwen2.5 72B, Q4_K_M (44.6 GB) offers the best balance of quality and VRAM usage. Q5_K_M (52.8 GB) provides better quality if you have the VRAM. The smallest option is IQ3_XS at 31.0 GB.
VRAM requirement by quantization
IQ3_XS31.0 GBIQ3_M33.7 GBIQ4_XS40.0 GBQ4_K_M ★44.6 GBQ5_K_M52.8 GBBF16146.4 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwen2.5 72B on a Mac?
Qwen2.5 72B requires at least 31.0 GB at IQ3_XS, 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 Qwen2.5 72B locally?
Yes — Qwen2.5 72B can run locally on consumer hardware. At Q4_K_M quantization it needs 44.6 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwen2.5 72B?
At Q4_K_M, Qwen2.5 72B can reach ~108 tok/s on AMD Instinct MI350X. 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 ÷ 44.6 × 0.65 = ~117 tok/s
Estimated speed at Q4_K_M (44.6 GB)
~117 tok/s~117 tok/s~108 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Qwen2.5 72B?
At Q4_K_M, the download is about 43.62 GB. The full-precision BF16 version is 145.41 GB. The smallest option (IQ3_XS) is 29.99 GB.
- Which GPUs can run Qwen2.5 72B?
No single consumer GPU has enough VRAM to run Qwen2.5 72B at Q4_K_M (44.6 GB). Multi-GPU or professional hardware is required.
- Which devices can run Qwen2.5 72B?
27 devices with unified memory can run Qwen2.5 72B at Q4_K_M (44.6 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), 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.