Qwen2.5 VL 72B Instruct — Hardware Requirements & GPU Compatibility
Vision
Qwen2.5-VL-72B-Instruct is Alibaba's 73-billion-parameter instruction-tuned vision-language model, the largest in the Qwen2.5-VL line. The card highlights recognition of text, charts and layouts in images, use as a visual agent for computer and phone control, comprehension of videos over an hour long with event pinpointing, bounding-box and point localization, and structured output for scans of invoices and tables. A model this size needs multi-GPU or a large unified-memory machine even when quantized. The card says the shipped config supports 32,768 tokens and describes extending it with YaRN for longer inputs. It is released under the Qwen license rather than Apache 2.0, so check its terms before commercial use. Published in January 2025, it follows Qwen2-VL, which the card says it improves on based on developer feedback.
75.0K downloads
658 likesSpecifications
- Publisher
- Alibaba
- Family
- Qwen 2.5
- Parameters
- 73.4B
- Architecture
- Qwen2_5_VLForConditionalGeneration
- Context Length
- 128,000 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2025-01-27
- License
- Other
Get Started
HuggingFace
How Much VRAM Does Qwen2.5 VL 72B Instruct Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 32.2 GB | 73.4 GB | 31.20 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 33.1 GB | 74.4 GB | 32.12 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 36.8 GB | 78.0 GB | 35.79 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 37.7 GB | 79.0 GB | 36.71 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 45.0 GB | 86.3 GB | 44.05 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 53.3 GB | 94.5 GB | 52.31 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 61.5 GB | 102.8 GB | 60.56 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 74.4 GB | 115.7 GB | 73.41 GB | 8-bit quantization, near-lossless |
Which GPUs Can Run Qwen2.5 VL 72B Instruct?
Q4_K_M · 45.0 GBQwen2.5 VL 72B Instruct (Q4_K_M) requires 45.0 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 59+ GB is recommended. Using the full 128K context window can add up to 41.3 GB, bringing total usage to 86.3 GB. No single GPU has enough memory — multi-GPU or cluster setups are needed.
Which Devices Can Run Qwen2.5 VL 72B Instruct?
Q4_K_M · 45.0 GB26 devices with unified memory can run Qwen2.5 VL 72B Instruct, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio M4 Max (64 GB).
Runs great
— Plenty of headroom
Where to Download Qwen2.5 VL 72B Instruct
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Qwen2.5 VL 72B Instruct need?
Qwen2.5 VL 72B Instruct requires 45.0 GB of VRAM at Q4_K_M, or 147.8 GB at BF16. Full 128K context adds up to 41.3 GB (86.3 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 73.4B × 4.8 bits ÷ 8 = 44 GB
KV Cache + Overhead ≈ 1 GB (at 2K context + ~0.3 GB framework)
KV Cache + Overhead ≈ 42.3 GB (at full 128K context)
VRAM usage by quantization
Q4_K_M45.0 GBQ4_K_M + full context86.3 GB- Can NVIDIA GeForce RTX 4090 run Qwen2.5 VL 72B Instruct?
Yes, at IQ2_S (23.9 GB) or lower. Higher quantizations like IQ2_M (25.8 GB) exceed the NVIDIA GeForce RTX 4090's 24 GB.
- What's the best quantization for Qwen2.5 VL 72B Instruct?
For Qwen2.5 VL 72B Instruct, Q4_K_M (45.0 GB) offers the best balance of quality and VRAM usage. Q5_0 (46.9 GB) provides better quality if you have the VRAM. The smallest option is IQ2_XXS at 21.2 GB.
VRAM requirement by quantization
IQ2_XXS21.2 GBQ2_K32.2 GBQ3_K_L38.6 GBQ4_K_M ★45.0 GBQ5_151.4 GBBF16147.8 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Qwen2.5 VL 72B Instruct on a Mac?
Qwen2.5 VL 72B Instruct requires at least 21.2 GB at IQ2_XXS, 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 VL 72B Instruct locally?
Yes — Qwen2.5 VL 72B Instruct can run locally on consumer hardware. At Q4_K_M quantization it needs 45.0 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Qwen2.5 VL 72B Instruct?
At Q4_K_M, Qwen2.5 VL 72B Instruct can reach ~107 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 ÷ 45.0 × 0.65 = ~116 tok/s
Estimated speed at Q4_K_M (45.0 GB)
~116 tok/s~116 tok/s~107 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 VL 72B Instruct?
At Q4_K_M, the download is about 44.05 GB. The full-precision BF16 version is 146.82 GB. The smallest option (IQ2_XXS) is 20.19 GB.
- Which GPUs can run Qwen2.5 VL 72B Instruct?
No single consumer GPU has enough VRAM to run Qwen2.5 VL 72B Instruct at Q4_K_M (45.0 GB). Multi-GPU or professional hardware is required.
- Which devices can run Qwen2.5 VL 72B Instruct?
27 devices with unified memory can run Qwen2.5 VL 72B Instruct at Q4_K_M (45.0 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.