Browse, search, and compare AI models from providers worldwide.
Deployment here means the real path to start using a model: through a managed runtime, on a rented server you control, or on your own machine.
Hosted for you
You can start without renting or managing your own server.
Cloud server you control
You rent the machine and manage setup, uptime, and GPU cost yourself.
On your computer
It runs locally, but larger open models may still need a real desktop GPU. When we can estimate it, model deploy surfaces show rough GPU memory guidance too.
Showing 4 active models
| # | Model | Category | Params | Score | Downloads | Likes | Cheapest Verified | Est. Value | Open |
|---|---|---|---|---|---|---|---|---|---|
| 168 | Qwen VL PlusQwen | Vision | Unknown | 22.0 | 0 | 0 | $0.1365/M Cheapest verified | $21M | |
| 173 |
Qwen VL MaxQwen |
| Vision |
| Unknown |
| 33.3 |
| 0 |
| 0 |
$0.5200/M Cheapest verified |
| $51M |
| — | Qwen3 VL 8B ThinkingQwenSelf-Host | Vision | 8B | — | 0 | 0 | Custom Start Free Trial | --- |
| — | Qwen3 VL 32B InstructQwenSelf-Host | Vision | 32B | — | 0 | 0 | Custom Start Free Trial | --- |