TENCENT PUB_DATE: 2026.08.30

TENCENT’S HY4: 1M‑TOKEN OPEN‑WEIGHT MODEL FOR REPO‑SCALE AGENTS

Tencent released the open-weight Hy4 LLM with a 1M-token context window, signaling a push toward self-hosted, long-context coding and agent workflows. Hy4 is a...

Tencent’s Hy4: 1M‑token open‑weight model for repo‑scale agents

Tencent released the open-weight Hy4 LLM with a 1M-token context window, signaling a push toward self-hosted, long-context coding and agent workflows.

Hy4 is an open-weight, text-only model with 770B total parameters (49B active), a 1M-token context, and weights hosted on Hugging Face—detailed in Simon Willison’s write-up of the Hy4 preview. The chat template exposes a simple reasoning_effort switch: "high" (default) or "no_think," which changes how much internal reasoning the model does.

If you’re building repo-scale agents, long logs analysis, or fewer-RAG pipelines, this is worth a look. Pair this with a refresher on agentic workflows and keep verification top of mind given rising change velocity highlighted by The New Stack’s piece on code verification strain link.

[ WHY_IT_MATTERS ]
01.

Hy4’s 1M-token context lets you load entire services, playbooks, or long logs to cut back on brittle retrieval layers.

02.

Open weights mean on-prem control and auditability, but you’ll need serious storage and inference planning.

[ WHAT_TO_TEST ]
  • terminal

    Benchmark "high" vs "no_think" reasoning_effort on latency, cost, and accuracy for end-to-end change requests over full repos.

  • terminal

    Prototype a repo-scale agent: pack code + docs + tests into context and compare against your current RAG setup for precision and regressions.

[ BROWNFIELD_PERSPECTIVE ]

Legacy codebase integration strategies...

  • 01.

    Start via a hosted gateway (e.g., OpenRouter) to gauge quality and throughput before committing GPU/IO budgets for self-hosting.

  • 02.

    Model the infra bill: 1.56TB weights and 1M-context inference stress storage, memory, and job schedulers; plan shard/stream strategies.

[ GREENFIELD_PERSPECTIVE ]

Fresh architecture paradigms...

  • 01.

    Design agents around long-context first: batch artifacts per task to minimize retrieval complexity and reduce cross-service chatter.

  • 02.

    Expose a toggle for reasoning depth (high vs no_think) so pipelines can trade accuracy for throughput per job class.

Enjoying_this_story?

Get daily TENCENT + SDLC updates.

  • Practical tactics you can ship tomorrow
  • Tooling, workflows, and architecture notes
  • One short email each weekday

FREE_FOREVER. TERMINATE_ANYTIME. View an example issue.

GET_DAILY_EMAIL
AI + SDLC // 5 MIN DAILY