# Xing4.0-29B-Intent (TeleAI — open-weights intent/extraction MoE)

> Updated 2026-10-20 · type: tool · category: ai-infrastructure · status: active · rev 1

Xing4.0-29B-Intent is TeleAI's Apache-2.0 29B MoE (~4B active) for schema-guided intent, NER and extraction to structured JSON, with open weights to self-host.

- Open source: yes (Apache-2.0)
- Self-hostable: yes
- Pricing: Free open weights under Apache-2.0; you pay only your own compute to run it, not a per-call extraction API.
- Best for: A technical founder or lean GTM/RevOps team that needs to turn messy inbound text (emails, replies, forms, transcripts) into structured JSON — intent, slots, entities, relations — on weights it self-hosts rather than a metered closed API.
- Not for: Teams that want a general chat assistant, that lack the GPU budget to serve a 29B MoE, or that need a vendor-supported hosted endpoint with an SLA.
- Last verified: 2026-10-21

- **Canonical:** https://gtmstacker.com/registry/tool/xing4-0-29b-intent/
- **Source:** [github · XingChen-AGI/Xing4.0-29B-A4B](https://github.com/XingChen-AGI/Xing4.0-29B-A4B) — Chinazhidx
- **Tags:** ai-infrastructure, llm, model-release, self-hostable, open-source, data-scraping
- **Repository:** https://github.com/XingChen-AGI/Xing4.0-29B-A4B

## Is Xing4.0-29B-Intent (TeleAI — open-weights intent/extraction MoE) open source?

Yes, Xing4.0-29B-Intent (TeleAI — open-weights intent/extraction MoE) is open source under the Apache-2.0 license.

## How much does Xing4.0-29B-Intent (TeleAI — open-weights intent/extraction MoE) cost?

Free open weights under Apache-2.0; you pay only your own compute to run it, not a per-call extraction API. (free).

## Can I self-host Xing4.0-29B-Intent (TeleAI — open-weights intent/extraction MoE)?

Yes, Xing4.0-29B-Intent (TeleAI — open-weights intent/extraction MoE) can be self-hosted (the source is available under the Apache-2.0 license).


---

An Apache-2.0, self-hostable **29B-total mixture-of-experts** model (~4B active) from China Telecom's **TeleAI**, specialised for **schema-guided intent recognition, slot filling, NER, and relation/event extraction into structured JSON**. It ships open weights in Safetensors, plus FP8 and GGUF packings, and the base repo documents vLLM, SGLang and KTransformers deployment. It arrives with a companion **XingIntent SDK** (GitHub) and a **Xing4.0-29B-Intent-oss** dataset (Hugging Face), both also Apache-2.0 — so the model, its tooling, and its training-data sample are all open.

## Provenance

- SPDX **apache-2.0** read directly from the **Xing4.0-29B-Intent model-card metadata** — not guessed, and not assumed-inherited from the base model. Apache-2.0 is OSI-approved, permissive and commercial-clean.
- Published by the official **XingChen-AGI** org (China Telecom AI / TeleAI), the same org as the **Xing4.0-29B-A4B** base model, so provenance is consistent. The companion **XingIntent SDK** (GitHub) and the **Xing4.0-29B-Intent-oss** dataset (HF) are both Apache-2.0.
- Self-hostable and free: weights are downloadable in Safetensors with FP8 and GGUF packings; the base repo carries vLLM / SGLang / KTransformers deployment docs. Open weights under Apache-2.0 mean the only cost is your own compute, not a metered API.
- Current activity: the Intent variant shows 46 downloads/mo and 15 likes; the base A4B model shows 37.5k downloads, 1.85k likes and 99 GitHub stars; the model was updated roughly four days before verification.
- **Vendor-claim, not verified:** the viral post's benchmark-superiority claims (beating Gemini-3.6-Flash / GPT-5.6-Sol) are the project's own and were not independently reproduced here.
- Surfaced via the 2026-10-21 X pull (post by Chinazhidx). Verification was performed against the primary source (the Intent model card, the base repo, the SDK and dataset cards) as untrusted content; no injected instructions were encountered. Curated from the GTM Stacker signal registry (run 2026-10-21-registry-update-01); license, org provenance, weights and self-hostability independently verified 2026-10-21.

## Why it matters for a GTM stack

A large share of RevOps plumbing is the same quiet job: take unstructured inbound text — a reply, a form, a call transcript — and turn it into fields a system can act on (what does this person want, which product, which fields to fill, who and what is named). The default is a metered closed extraction API that owns that step. Xing4.0-29B-Intent is the own-your-stack alternative: an Apache-2.0 MoE purpose-built for schema-guided intent, slot filling, NER and relation/event extraction to structured JSON, with open weights and documented local serving. The honest read: the headline "beats Gemini / GPT" benchmark is the vendor's own and not reproduced here, the Intent variant is new with light adoption so far, and a 29B-total MoE still needs real GPU budget to serve. What is verified is what governs adoption: Apache-2.0 read from the model card, a consistent first-party TeleAI org, open Safetensors/FP8/GGUF weights, and documented self-host paths.