Skip to content
AI Atlas
ModelActiveOpen weightsIdentity probable

Hy4 preview

Tencenthuggingface.co/tencent/Hy4-preview

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

Open in Graph
data quality68

Updated 3 h ago · first seen 11 Sept 2026

model_01M294WVPRVK9PVYGKXRK6Y510

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
1
API aliases
tencent/hy4-previewIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
0Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Open weights— weights downloadable under Apache-2.0; commercial use allowed; redistribution allowed; derivatives allowed; 4 dimensions unknown.

Weights downloadable under a permissive or Creative Commons licence allowing commercial use; code or data may be missing.

  • Weights

    Yes

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    Yes

  • Redistribution

    Yes

  • Derivatives

    Yes

Licence: Apache License 2.0 (permissive · SPDX Apache-2.0)

dimensions marked null are unknown, not false

Key facts

Release date

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 h agomedium

Model card
huggingface.co/tencent/Hy4-preview

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 6 d agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 21 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 6 d agomedium

Capabilities

Modalities

Modalities
text
Input
text
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Yes

    OpenRouter public model & pricing listing · T2

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 6 d agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 6 d agomedium

Providers & Pricing1

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inOutput / 1MStatusObservedSource
OpenRoutercheapest outputtencent/hy4-preview1.05Mout 64K$0.042active2 h agosince 11 Sept 2026openrouter.aiT2

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 1 provider

Output price history of Hy4 preview$0$1$2$3Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $2.5 · 11 Sept 2026
  • OpenRouter
  • OpenRouterfirst observed $2.511 Sept 2026

Input price · USD / 1M tokens 1 provider

Input price history of Hy4 preview$0$0.20$0.40$0.60$0.80$1Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26Sept 26OpenRouter: first observed → $0.834 · 11 Sept 2026
  • OpenRouter
  • OpenRouterfirst observed $0.83411 Sept 2026

Hardware fit37

Estimated

3 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—449.0 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—449.0 GB est.Yes
NVIDIA DGX B2004bit1,440 GB449.0 GB est.Yes
Apple M2 Ultra4bit—449.0 GB est.No
Apple M1 Ultra4bit—449.0 GB est.No
Apple M3 Max4bit—449.0 GB est.No
Apple M4 Max4bit—449.0 GB est.No
Mac Studio (Apple M5 Max)4bit—449.0 GB est.No
MacBook Pro (Apple M5 Max)4bit—449.0 GB est.No
Apple M2 Max4bit—449.0 GB est.No
Apple M1 Max4bit—449.0 GB est.No
Apple M4 Pro4bit—449.0 GB est.No
Mac mini (Apple M5 Pro)4bit—449.0 GB est.No
MacBook Pro (Apple M5 Pro)4bit—449.0 GB est.No
Apple M3 Pro4bit—449.0 GB est.No
Apple M1 Pro4bit—449.0 GB est.No
Apple M2 Pro4bit—449.0 GB est.No
Apple M44bit—449.0 GB est.No
iMac (Apple M4)4bit—449.0 GB est.No
Mac mini (Apple M6)4bit—449.0 GB est.No
MacBook Air (Apple M5)4bit—449.0 GB est.No
MacBook Pro (Apple M5)4bit—449.0 GB est.No
Apple M24bit—449.0 GB est.No
Apple M34bit—449.0 GB est.No
Apple M14bit—449.0 GB est.No
NVIDIA GeForce RTX 30904bit24 GB449.0 GB est.No
NVIDIA GeForce RTX 40904bit24 GB449.0 GB est.No
NVIDIA GeForce RTX 50904bit32 GB449.0 GB est.No
NVIDIA A100 80GB4bit80 GB449.0 GB est.No
NVIDIA H100 SXM4bit80 GB449.0 GB est.No
NVIDIA H100 NVL4bit94 GB449.0 GB est.No
NVIDIA DGX Spark4bit128 GB449.0 GB est.No
NVIDIA H2004bit141 GB449.0 GB est.No
NVIDIA H200 NVL4bit141 GB449.0 GB est.No
NVIDIA B2004bit180 GB449.0 GB est.No
AMD Instinct MI300X4bit192 GB449.0 GB est.No
AMD Instinct MI325X4bit256 GB449.0 GB est.No
Assumptions (7)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
  • Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.

Versions & Artifacts0

Version history

Context windowfirst observation only

11 Sept 2026current

Licensefirst observation only

17 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Opennessfirst observation only

12 Sept 2026current

Parametersfirst observation only

17 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Papers2

Timeline1

Full timeline →
  • Release date changedModelHy4 previewTencent

    Hy4 preview: release date changed from 2026-08-28 to 2026-08-27

    Release date28 Aug 2026→27 Aug 2026huggingface
    huggingface.co

Change history36

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 17 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Attributes as of 17 Sept 2026 33 claims in force

Release date
27 Aug 2026
Openness
open-weights
License
Apache-2.0
Architecture
HYV4ForCausalLM
Parameters
780B
Context window
1.05M tokens
Max output
64K tokens
Modalities
text
Input modalities
text
Output modalities
text
File size
1560.0 GB
Hugging Face repo
tencent/Hy4-preview
Pipeline tag
text-generation
Downloads
13,581
Likes
480
Access
open
Last modified
2026-08-28T14:58:32+00:00
Library name
transformers
License key
Apache-2.0
License raw
apache-2.0
Downloads all time
13,581
Model type
hy_v4
Openrouter id
tencent/hy4-preview
Openrouter listed at
28 Aug 2026
Reasoning
Yes
Structured output
Yes
Supported parameters
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, temperature, tool_choice, tools
Tags
hunyuan, hy4, hy_v4, moe, safetensors, text-generation, transformers
Tool calling
Yes
Weights available
Yes
Weights dtype
BF16, F32
36 claims · 33 properties

Release daterelease_date2

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
27 Aug 2026 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
28 Aug 2026 → supersededOpenRouter public model & pricing listingT2mediumdeterministic

Opennessopenness1

Claim history for Openness
ValueValid from → toStatusSourceConfidenceExtractor
open-weights → currentcurrentAI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2highderived

Licenselicense1

Claim history for License
ValueValid from → toStatusSourceConfidenceExtractor
Apache-2.0 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Architecturearchitecture1

Claim history for Architecture
ValueValid from → toStatusSourceConfidenceExtractor
HYV4ForCausalLM → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Parametersparameter_count1

Claim history for Parameters
ValueValid from → toStatusSourceConfidenceExtractor
780B → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Context windowcontext_length1

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
1.05M tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Max outputmax_output_tokens1

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
64K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Modalitiesmodalities1

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

File sizefile_size_gb1

Claim history for File size
ValueValid from → toStatusSourceConfidenceExtractor
1560.0 GB → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
tencent/Hy4-preview → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Pipeline tagpipeline_tag1

Claim history for Pipeline tag
ValueValid from → toStatusSourceConfidenceExtractor
text-generation → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model cardmodel_card_url1

Claim history for Model card
ValueValid from → toStatusSourceConfidenceExtractor
https://huggingface.co/tencent/Hy4-preview → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloadsmetric.downloads1

Claim history for Downloads
ValueValid from → toStatusSourceConfidenceExtractor
13,581 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Likesmetric.likes3

Claim history for Likes
ValueValid from → toStatusSourceConfidenceExtractor
482 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
481 → supersededHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic
480 → supersededHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Accessaccess1

Claim history for Access
ValueValid from → toStatusSourceConfidenceExtractor
open → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that... → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Last modifiedlast_modified1

Claim history for Last modified
ValueValid from → toStatusSourceConfidenceExtractor
2026-08-28T14:58:32+00:00 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Library namelibrary_name1

Claim history for Library name
ValueValid from → toStatusSourceConfidenceExtractor
transformers → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

License keylicense_key1

Claim history for License key
ValueValid from → toStatusSourceConfidenceExtractor
Apache-2.0 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

License rawlicense_raw1

Claim history for License raw
ValueValid from → toStatusSourceConfidenceExtractor
apache-2.0 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Downloads all timemetric.downloads_all_time1

Claim history for Downloads all time
ValueValid from → toStatusSourceConfidenceExtractor
13,581 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Model typemodel_type1

Claim history for Model type
ValueValid from → toStatusSourceConfidenceExtractor
hy_v4 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
tencent/hy4-preview → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter listed atopenrouter_listed_at1

Claim history for Openrouter listed at
ValueValid from → toStatusSourceConfidenceExtractor
28 Aug 2026 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Reasoningreasoning1

Claim history for Reasoning
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Structured outputstructured_output1

Claim history for Structured output
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, temperature, tool_choice, tools → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tagstags1

Claim history for Tags
ValueValid from → toStatusSourceConfidenceExtractor
hunyuan, hy4, hy_v4, moe, safetensors, text-generation, transformers → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Tool callingtool_calling1

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Weights availableweights_available1

Claim history for Weights available
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentAI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2highderived

Weights dtypeweights_dtype1

Claim history for Weights dtype
ValueValid from → toStatusSourceConfidenceExtractor
BF16, F32 → currentcurrentHugging Face Hub (public pages, model cards, papers)T2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

33

Source tiers

T233

Freshest observation

4 h ago

Conflicts

None

Source documents 3

Source documents
SourceDocumentTypeTierLast observedSnapshots
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary2 h ago99
Hugging Face Hub (public pages, model cards, papers)huggingface.co/tencent/Hy4-preview model_pageT2· Quality secondary4 h ago5
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=tencent&p=0&sort=downloads listingT2· Quality secondary4 h ago40

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (68/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →