by Baichuan Inc.

Baichuan2-13B.

text open weights laptop+ 13B params 4K ctx Transformer
Smallest GPU
1× Nvidia RTX 3080

Bilingual EN/ZH open-weight. Strong for its size on Chinese-language benchmarks.

Smallest GPU to run it See all quantisations →

1× Nvidia RTX 3080.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
Self-hosted on rented GPU cluster self hosted Run yourself →
Self-hosted on rented GPU cluster self hosted Run yourself →
SiliconFlow hosted inference Launch ↗
SiliconFlow hosted inference Launch ↗
Sources

Official references.

FAQ

Frequently asked.

How do I run Baichuan2-13B?
Baichuan2-13B 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 Baichuan2-13B?
Baichuan2-13B is available via Self-hosted on rented GPU cluster, SiliconFlow. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Baichuan2-13B?
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 Baichuan2-13B open-source or proprietary?
Baichuan2-13B is open-weight under the Baichuan2 Community License license. You can download and self-host it.