Phi-3.5 Mini is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.

Where can I access Phi-3.5 Mini?

Phi-3.5 Mini's access providers haven't been catalogued yet on RentGPU. Check the maker's documentation for official endpoints.

How much does it cost to run Phi-3.5 Mini?

Self-hosting cost depends on the GPU you rent and the throughput you need. See the Run It Yourself tab for GPU configurations and hourly cost estimates.

Is Phi-3.5 Mini open-source or proprietary?

Phi-3.5 Mini is open-weight under the MIT license. You can download and self-host it.

Run it yourself

Cheapest hardware per quantisation.

Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.

Quantisation	Cheapest GPU config	Total VRAM	Live $/hr	tokens/sec
FP16 FP16 — half precision (default)	1× Nvidia RTX 3080	10 GB	—	—	Compare →
FP8 FP8 — 8-bit float (Hopper / Blackwell)	1× Nvidia Nvidia P102-100	5 GB	—	—	Compare →
INT4 INT4 — 4-bit integer (~4× VRAM saving)	1× Nvidia Nvidia Titan V	3 GB	—	—	Compare →

Just need an API?

Skip the GPU rental and call a hosted endpoint instead. See access providers on the Overview tab →

Phi-3.5 Mini.

1× Nvidia Titan V.

Official references.

Variants in the Phi family.

Workloads.

Frequently asked.

Cheapest hardware per quantisation.

How much it can remember.

What it can do.