Claim · 2024-11-04 · publication · Stated in source · Supported

Tencent's Hunyuan Team posted the Hunyuan-Large technical report to arXiv on 4 November 2024 (version 1), describing a mixture-of-experts model with 389 billion total and 52 billion activated parameters and stating that its code and checkpoints are released.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Tencent / 腾讯 → published → Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

Tencent / 腾讯published ↓Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2024-11-04 · publication Records dated 2024 →

Scope and limitsParameter counts are the report's own description. The licence states a release date of November 5, 2024 for Tencent-Hunyuan-Large; the weights' upload dates were not checked. Performance claims are not recorded.

The evidence 03

primary sourceSupports the claim

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

arXiv · 2024-11-04

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“Tencent Hunyuan Team”

Location in source Title page

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Tencent Hunyuan Team
Version: Dated document, retrieved on 2026-10-29 (SHA-256 c5267a6a0b7d9a091d51eb83f8dda3dc997dd4abb5570d41d184afde84177512) directly from the publisher. Version: 2411.02265v1. Version 1 as submitted on 4 November 2024; versions 2 and 3 (latest 6 November 2024) not inspected.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Tencent Hunyuan Team, “Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent”, 2024-11-04.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, Chinese frontier-AI institutions, third collection (research/china-labs-3). The quotation (3 words) matched the text retrieved for the candidate pack on 2026-10-29 and again in a fresh retrieval the same day, read directly from the publisher. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review.

primary sourceSupports the claim

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

arXiv · 2024-11-04

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“with a total of 389 billion parameters and 52 billion activation parameters”

Location in source Abstract

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Tencent Hunyuan Team
Version: Dated document, retrieved on 2026-10-29 (SHA-256 c5267a6a0b7d9a091d51eb83f8dda3dc997dd4abb5570d41d184afde84177512) directly from the publisher. Version: 2411.02265v1. Version 1 as submitted on 4 November 2024; versions 2 and 3 (latest 6 November 2024) not inspected.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Tencent Hunyuan Team, “Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent”, 2024-11-04.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, Chinese frontier-AI institutions, third collection (research/china-labs-3). The quotation (12 words) matched the text retrieved for the candidate pack on 2026-10-29 and again in a fresh retrieval the same day, read directly from the publisher. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review.

primary sourceSupports the claim

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

arXiv · 2024-11-04

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“The code and checkpoints of Hunyuan-Large are released to facilitate future innovations and applications.”

Location in source Abstract

How it was read Retrieved directly from the publisher

Machine-checked · 2026-10-31

Source details and check notes

Authors: Tencent Hunyuan Team
Version: Dated document, retrieved on 2026-10-29 (SHA-256 c5267a6a0b7d9a091d51eb83f8dda3dc997dd4abb5570d41d184afde84177512) directly from the publisher. Version: 2411.02265v1. Version 1 as submitted on 4 November 2024; versions 2 and 3 (latest 6 November 2024) not inspected.
Canonical address: Open the canonical source ↗
Accessed: 2026-10-29
Language: English (en)
Attribution: Tencent Hunyuan Team, “Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent”, 2024-11-04.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, Chinese frontier-AI institutions, third collection (research/china-labs-3). The quotation (14 words) matched the text retrieved for the candidate pack on 2026-10-29 and again in a fresh retrieval the same day, read directly from the publisher. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. Publication of a specific document or version. Publication of a policy is not evidence of implementation.

Date. Submission date of arXiv version 1; not the release date of the model or its weights.

Record ID c3-tencent-hunyuan-large-report