Pyyan / Compare / Hy4 preview vs Muse Spark Open

Hy4 preview vs Muse Spark Open

2 of 5

Open-Weight Models · verified 20 Oct 2026

Hy4 previewTencentcurrent
Muse Spark OpenMetacurrent
3 slots left
SpecificationHy4 previewMuse Spark Open
Summary770B parameters under Apache 2.0, and it helped optimise its own training.The largest American open weights, under a licence with a revenue trigger.
Context1M1M
Input ($/Mtok)$0.834Weights only
Output ($/Mtok)$2.501Weights only
LicenceApache 2.0Muse Model License
Max output64KNot published
Parameters770B total, 49B active816B total, 42B active
Released28 Aug 202615 Oct 2026
Model IDtencent/Hy4-previewmeta-models/Muse-Spark-Open-816B-A42B
CategoryOpen-Weight ModelsOpen-Weight Models
Official—Meta ↗

Highlighted rows are where these differ.

Hy4 preview

  • 770B total parameters with 49B active, 78 layers, 256 routed experts plus one shared
  • Apache 2.0, with an FP8 quantised build shipped alongside it
  • Tencent used it during its own development, and report a 31.8% inference throughput gain from it

Best for the largest open weights.

Full spec sheet →

Muse Spark Open

  • Text, image, video and audio in, text out, with a 1M token context
  • Muse Model License, not open source: attribution required, and a separate agreement above $20m of model-service revenue
  • About 1.5TB in BF16, or two Mac Studios at 4-bit

Best for multimodal work you host yourself.

Full spec sheet →