Qwen2.5-VL-7B-Instruct
Qwen2.5-VL-7B-Instruct is an open-weight vision and language model from Alibaba Qwen with 8.3B parameters. At 4-bit it needs about 6 GB of memory, so the smallest current device that fits it is the Mac mini M6 (16GB).
Overview
Includes room for an 8k context and runtime overhead. More context needs more memory.
Key information
- Lab
- Alibaba Qwen
- Released
- 26 Jan 2025
- Parameters
- 8.3B
- Type
- Vision and language
- Context
- 128,000 tokens
- License
- Apache-2.0
- HF downloads, 30 days
- 5,824,540
- Repository
- Qwen/Qwen2.5-VL-7B-Instruct
More from Alibaba Qwen
View allWill it run on your hardware?
How we estimate| Estimate or device | Memory |
|---|---|
| Q4 | 6 GB |
| Q8 | 10.2 GB |
| BF16 | 18.8 GB |
| RTX 5060 Ti 16 GB | 16 GB usable |
| RTX 5090 32 GB | 32 GB usable |
| DGX Spark 128 GB | 108.8 GB usable |
| Mac Studio M5 Ultra 256 GB | 192 GB usable |
Single-device memory estimate. Pick a device to update the On your device column.
36 GB usable memory
| Format | Memory needed | On your device | Example hardware |
|---|---|---|---|
| 4-bit (Q4) | ≈ 6 GB | Fits 17% | Mac mini M6 (16GB)16 GB memory |
| 8-bit (Q8) | ≈ 10.2 GB | Fits 28% | GeForce RTX 5060 Ti 16GB16 GB memory |
| 16-bit (BF16) | ≈ 18.8 GB | Fits 52% | Arc Pro B6024 GB memory |
Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.
Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.
Where to run it
On a Mac
Start with the MLX files, built for Apple Silicon.
mlx-community/Qwen2.5-VL-7B-Instruct-4bitCheck your MacWith GGUF
Choose a file for llama.cpp or a compatible app.
unsloth/Qwen2.5-VL-7B-Instruct-GGUFFind compatible hardwareThrough an API
No hosted API found.
mlx_vlm.generate --model mlx-community/Qwen2.5-VL-7B-Instruct-4bit \
--prompt "Describe this image." --image image.jpgllama-cli -hf unsloth/Qwen2.5-VL-7B-Instruct-GGUF \
-c 8192 -p "Explain how a transformer works."Example commands built from the repository ids above. They need a working install of MLX or llama.cpp. We have not run them; check each repository for available files.
More about this model
Frequently asked questions
How much memory does Qwen2.5-VL-7B-Instruct need? At an 8k context, about 6 GB at 4-bit, 10.2 GB at 8-bit and 18.8 GB at 16-bit (BF16). A longer context needs more.
Can I run Qwen2.5-VL-7B-Instruct on a Mac? The smallest current Mac that fits the 4-bit estimate of 6 GB is the Mac mini M6 (16GB). An MLX build is available: mlx-community/Qwen2.5-VL-7B-Instruct-4bit.
Does the full context fit? Qwen2.5-VL-7B-Instruct supports up to 128,000 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.
What does it cost through an API? We did not find a hosted API for this model.
License in plain English
Apache-2.0. This license permits commercial use, modification and redistribution, with conditions such as keeping the required notices. This summary is not legal advice.
OMHQ RigBench
Not yet tested. We show no speed or quality score without a measurement.
Revision history and sources
Last updated . Sources:Hugging Face model card, MLX repository, GGUF repository.