Qwen 2.5 3B 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 Qwen 2.5 3B?

Qwen 2.5 3B is available via Alibaba DashScope, Ollama. Each access option lists its own pricing (per million tokens or hourly hosting).

How much does it cost to run Qwen 2.5 3B?

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 Qwen 2.5 3B open-source or proprietary?

Qwen 2.5 3B is open-weight under the Qwen License 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 Nvidia GeForce RTX 3070Ti	8 GB	—	—	Compare →
FP8 FP8 — 8-bit float (Hopper / Blackwell)	1× Nvidia Nvidia P104-100	4 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 →

Qwen 2.5 3B.

1× Nvidia Titan V.

Cheapest hosted endpoints.

Official references.

Variants in the Qwen family.

Workloads.

Frequently asked.

Cheapest hardware per quantisation.

How much it can remember.

What it can do.