Skip to model comparison
AI Agent Store/Model comparisonsBuild an AI worker ↗

XingChen / China Telecom · Download verified

Xing4.0 29B Intent

Turn a request such as “find flights tomorrow” into a category and fields your application can use. Supply your categories, field descriptions and text or conversation.

First reviewed 2026-10-21 · Checked 2026-11-03. The launch date has not been confirmed.

We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on records with known answers, including cases that should go to a person.

Runs onYour hardwareHardware and setup costs apply
Documented capacityNot verifiedSee input limits below

What you can use today

You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.

Exact download ID: XingChen-AGI/Xing4.0-29B-Intent. Returns JSON containing categories and extracted arguments. Chinese and English examples cover intent, entities, relations and events. This is structured extraction, not a fixed-choice probability model.

Apache 2.0 weights and companion software. Roughly 29B total parameters with about 4B active per token still require storage for all weights. The repository was created October 15 and updated October 20; its exact release day remains unverified. SGLang and vLLM require the publisher’s separate plugin; an unmodified installation does not recognize this model.

The checkpoint configuration lists 262,144 positions, but the specialized instructions do not establish a validated task input or output limit. Check your serving setup and real documents.

No hosted price verified. FP8 and GGUF are formats of this model, not additional base releases.

Provider release and specifications ↗

Check availability and plans ↗

Test it before switching

Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.

Compare caching and long-context costs ↗
AI Agent Store · Model comparisons · Data reviewed 2026-11-03Sources, limitations & corrections ↗