Menu

Hy4-preview 780B: sovereign deep reasoning, no third-party API
📰

Hy4-preview 780B: sovereign deep reasoning, no third-party API

DEV Community: security·Matheus Feijão·about 17 hours ago
#S7rzJazt
#devtosecurity#devto#dev#reasoning#high
Long article (568 words) — no AI summary yet.
Reading 0:00
15s threshold

Short answer

Hy4-preview is Beans Tech's own model: 780B parameters , hyv4 architecture, native Portuguese and a 1M-token trained context. It runs on our own infrastructure with an OpenAI-compatible API — no data ever leaves for a third-party API. It is the Deep tier: heavy reasoning for the highest-consequence tasks.

TL;DR

780B, Q4_K_M, served by llama.cpp with a custom patch; text→text.

3 reasoning modes : no_think (direct), low (short reasoning) and high (deep) — via chat_template_kwargs.reasoning_effort .

64 concurrent slots with continuous batching; 200 simultaneous requests answered in ~12s (200/200 HTTP 200).

TTFT ~150–205 ms; ~25 tok/s per stream; ~65–70 tok/s aggregate under load.

Tool calling with parallel calls; SSE streaming.

Sovereign: self-hosted, LGPD by architecture — data crosses no border and no vendor.

Why build an own 780B model?

Because one class of task admits no outsourcing: contract analysis under judicial secrecy, opinions containing bank-secrecy data (LC 105), medical…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.