Reads photos, screenshots and documents. Made by Alibaba.
Qwen3 VL 8B is a vision model that can read images and screenshots from Alibaba. Reads photos, screenshots and documents. Running it locally needs about 6.9 GB of memory, and the download is 6.1 GB.
The least memory you need, by Apple chip:
Runs well on: RTX 3060 12GB, RTX 3070, RTX 3080 10GB, RTX 3090, RTX 4060, RTX 4060 Ti 16GB, RTX 4070 / 4070 Super, RTX 4070 Ti Super, RTX 4080 / 4080 Super, RTX 4090, RTX 5060, RTX 5060 Ti 16GB, RTX 5070, RTX 5070 Ti, RTX 5080, RTX 5090, Radeon RX 7800 XT, Radeon RX 9070 XT, Radeon RX 7900 XTX.
As an Amazon Associate I earn from qualifying purchases.
About 6.9 GB of video memory or unified memory (the download is 6.1 GB, plus room for the conversation). On a Mac, the smallest configuration that runs it is 8 GB.
A 16 GB M4 Mac runs it runs well at about 11 words a second. An 8 GB M1 Mac runs it slow at about 5 words a second.
Yes, the model is free to download. Its licence is listed as Apache 2.0. That is a permissive licence that allows commercial use.
Install Ollama, then run: ollama run qwen3-vl:8b
| Machine | Verdict | Speed |
|---|---|---|
| M1 8GB | Slow | 5 words/s |
| M4 16GB | Runs well | 11 words/s |
| M4 32GB | Runs well | 11 words/s |
| M4 Pro 48GB | Runs great | 23 words/s |
| M4 Max 128GB | Runs great | 47 words/s |
| M3 Ultra 512GB | Runs great | 71 words/s |
| RTX 4060 | Runs great | 20 words/s |
| RTX 4070/4070 Super | Runs great | 38 words/s |
| RTX 5070 Ti | Runs great | 66 words/s |
| RTX 3090 | Runs great | 69 words/s |
| RTX 5090 | Runs great | 132 words/s |
| Ryzen AI Max+ 395 128GB | Runs great | 19 words/s |
| CPU only 32GB | Slow | 5 words/s |