Qwen2.5-VL 7B Instruct
Alibaba · 8.3B · up to 125K context · apache-2.0
A capable everyday vision model that fits a 16GB Mac, able to read screenshots, charts, and dense documents rather than just describing photos. It also does basic video understanding and can point to bounding boxes, which most local vision models skip.
On a M4 Pro with 48 GB
macOS9.6 GBweights8.8 GBKV cache0.5 GBheadroom29.1 GB
- Weights
- 8.8 GB
- KV cache
- 0.5 GB
- Usable RAM
- 38.4 GB
- Headroom
- 29.1 GB
- Generation
- 24.1 tok/sest.
- Prompt processing
- 109 tok/sest.
- First token (1K prompt)
- 9.4 sest.
Decode speed is bandwidth ÷ active weight bytes, at 273 GB/s and 78% efficiency. These are modelled figures, not measurements.
Every quantization, on your Mac
| Quant | Weights | + KV | Verdict | Speed est. | Repo |
|---|---|---|---|---|---|
| q4 | 4.7 GB | 5.1 GB | FITS · 33.3 GB FREE | 45.6 tok/s | Qwen2.5-VL-7B-Instruct-4bit |
| q8 | 8.8 GB | 9.3 GB | FITS · 29.1 GB FREE | 24.1 tok/s | Qwen2.5-VL-7B-Instruct-8bit |
We never host weights. Every link goes to Hugging Face.
Run it
Chat
mlx_lm.chat --model mlx-community/Qwen2.5-VL-7B-Instruct-8bitServe an OpenAI-compatible endpoint
mlx_lm.server --model mlx-community/Qwen2.5-VL-7B-Instruct-8bit --port 8080How far can you push the context
2K tokensFITS · 29.5 GB FREE
cache 0.1 GB
8K tokensFITS · 29.1 GB FREE
cache 0.5 GB
32K tokensFITS · 27.7 GB FREE
cache 1.9 GB
Which Macs run this
| Chip | Smallest RAM that fits | Speed est. |
|---|---|---|
| M1 | 16 GB | 5.6 tok/s |
| M1 Pro | 16 GB | 17.2 tok/s |
| M1 Max | 32 GB | 35.8 tok/s |
| M1 Ultra | 64 GB | 73.5 tok/s |
| M2 | 16 GB | 8.3 tok/s |
| M2 Pro | 16 GB | 17.5 tok/s |
| M2 Max | 32 GB | 36.3 tok/s |
| M2 Ultra | 64 GB | 74.4 tok/s |
| M3 | 16 GB | 8.3 tok/s |
| M3 Pro | 18 GB | 12.8 tok/s |
| M3 Max (14-core CPU) | 36 GB | 26.5 tok/s |
| M3 Max (16-core CPU) | 48 GB | 36.3 tok/s |
| M3 Ultra | 96 GB | 77.1 tok/s |
| M4 | 16 GB | 10.1 tok/s |
| M4 Pro | 24 GB | 24.1 tok/s |
| M4 Max (14-core CPU) | 36 GB | 37.7 tok/s |
| M4 Max (16-core CPU) | 48 GB | 50.8 tok/s |
| M5 | 16 GB | 13.0 tok/s |
| M5 Prounverified | 24 GB | 27.5 tok/s |
| M5 Maxunverified | 36 GB | 57.8 tok/s |