# Tencent-Hunyuan/Tencent-Hunyuan-Large

Repository: https://github.com/Tencent-Hunyuan/Tencent-Hunyuan-Large
Canonical: https://ross.abutalabs.com/products/tencent-hunyuan-large
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-12-06T08:15:56+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 48
- inputs: {"age_days": 679, "days_push": 635, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1582, forks 119 (observed 2026-08-28T04:05:07.123998+00:00)

## What it is
Official repository for Tencent Hunyuan-Large, a 52B-parameter (A13B active) mixture-of-experts open-source large language model with up to 256K context. It provides model weights (pretrain and instruct variants, including FP8), inference code, and links to the technical report and hosted demo.

## Use cases
- download and self-host a large open-source MoE language model
- run Hunyuan-Large inference locally with vLLM or transformers
- fine-tune or continue pretraining from Hunyuan-Large base weights
- evaluate a 256K-context long-context LLM
- serve a chat assistant from open weights
- research mixture-of-experts architecture at scale

## When to choose
- you need a powerful open-weights MoE LLM with very long context
- you want to self-host or fine-tune a large Chinese/English bilingual model
- you are researching MoE scaling or FP8 inference

## When to avoid
- you need a small model that fits on consumer hardware
- you want a managed API without hosting infrastructure
- you need permissive licensing for commercial redistribution without checking terms

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, machine-learning, deep-learning
- domain: large-language-models, artificial-intelligence, machine-learning
- platform: python
- tags: moe, model-weights, hunyuan, tencent, open-weights, long-context, transformers, gpu, linux

## Member repositories
- Tencent-Hunyuan/Tencent-Hunyuan-Large (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:07.123998+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 2026-08-30T03:56:08.153389+00:00, confidence not recorded.
  - readme: https://github.com/Tencent-Hunyuan/Tencent-Hunyuan-Large (fetched 2026-08-28T04:05:07.123998+00:00, sha 6586adabe7a8)
- Data as of 2026-08-30T08:39:29.467469+00:00.