# baichuan-inc/Baichuan-13B

A 13B large language model developed by Baichuan Intelligent Technology

Repository: https://github.com/baichuan-inc/Baichuan-13B
Canonical: https://ross.abutalabs.com/products/baichuan-13b
Homepage: https://huggingface.co/baichuan-inc/Baichuan-13B-Chat
Language: Python
License: Apache-2.0
License Family: permissive
Topics: artificial-intelligence, chatgpt, chinese, gpt-4, huggingface, large-language-models, natural-language-processing, benchmark, ceval, mmlu
Last push: 2023-09-06T17:16:53+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 82
- inputs: {"age_days": 1150, "days_push": 1092, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2926, forks 229 (observed 2026-08-28T04:07:30.433403+00:00)

## What it is
Baichuan-13B is an open-source, commercially usable 13-billion-parameter large language model from Baichuan Intelligence, released as both a pre-trained base model and an aligned chat model. It is bilingual (Chinese/English), trained on 1.4 trillion tokens, and ships with int8/int4 quantized versions runnable on consumer GPUs like the RTX 3090.

## Use cases
- run a bilingual chinese-english chat llm locally
- download an open-source 13b base model for fine-tuning
- deploy a quantized llm on a consumer gpu
- benchmark chinese language model performance on ceval and mmlu
- self-host a chatgpt-style assistant
- fine-tune a commercially usable open llm

## When to choose
- you need a strong open 13B model with good Chinese performance
- you want both a pre-trained base and an aligned chat model
- you need int8/int4 quantization to fit consumer GPUs
- you need a permissively licensed model for commercial use (with approval)

## When to avoid
- you need the latest capabilities - Baichuan 2 supersedes this model
- you need multilingual support beyond Chinese and English
- you need a long context window beyond 4096 tokens
- you want commercial use without applying for a license

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: llm-inference, llm-training, chatbot
- domain: large-language-models, artificial-intelligence
- platform: python
- tags: open-weights, chinese-english-bilingual, quantization, huggingface, superseded-by-baichuan2, commercial-license-required, natural-language-processing, gpu, linux

## Member repositories
- baichuan-inc/Baichuan-13B (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:30.433403+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:33:36.391388+00:00, confidence not recorded.
  - readme: https://github.com/baichuan-inc/Baichuan-13B (fetched 2026-08-28T04:07:30.433403+00:00, sha 19d1f19f09d0)
  - homepage: https://huggingface.co/baichuan-inc/Baichuan-13B-Chat (fetched 2026-08-29T09:48:53.846517+00:00, sha c784f0b3fd50)
  - site_page: https://huggingface.co/docs (fetched 2026-08-29T09:48:53.849571+00:00, sha bdec26667b98)
  - site_page: https://huggingface.co/docs/inference-providers (fetched 2026-08-29T09:48:53.853536+00:00, sha 8a5d0f819473)
  - site_page: https://huggingface.co/docs/hub/model-cards (fetched 2026-08-29T09:48:53.855528+00:00, sha 60ded09a56b0)
  - site_page: https://huggingface.co/pricing (fetched 2026-08-29T09:48:53.851415+00:00, sha de6b7a178be5)
  - site_page: https://huggingface.co/huggingface (fetched 2026-08-29T09:48:53.857508+00:00, sha e33667a4f9ae)
- Data as of 2026-08-30T08:39:29.467469+00:00.