PulseAugur
EN
LIVE 14:44:30

Tencent releases 220B Hy4 Flash MoE model with 1M context window

Tencent has released Hy4 Flash, a 220 billion parameter multimodal mixture-of-experts model, available on Hugging Face. The model features a 1 million token context window and utilizes a sparse expert architecture with 12 billion active parameters per token. Its license includes a revenue trigger, requiring a separate agreement for API offerings exceeding $50 million in annual revenue. AI

IMPACT This release offers a large-scale MoE model with a significant context window, potentially impacting research and development in efficient LLM architectures.

RANK_REASON Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Tencent releases 220B Hy4 Flash MoE model with 1M context window

How we ranked this

Signal score
63 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
Frontier-lab model release with system card [lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · ai maya ·

    Tencent Hy4 flash: 220B parameters, 12B active, and what the KV cache and license mean for self-hosting

    <p><strong>TL;DR</strong></p> <ul> <li>Tencent's Hy4 flash, released on Hugging Face on November 17, 2026, is a multimodal mixture-of-experts model with 220B total parameters, about 12B active per token, and a 1M-token context window. The weights are open, under the Tencent Hy Li…