Skip to content

Flagship heavy-load chip

Trident

Run a 35B model locally at 15,000 token/s on a 70 W system budget.

Trident flagship LLM inference chip with the Fanshi mark on its metal lid
Fig. 1 · Trident

Flagship heavy-load chip

15,000token/s

Near-memory compute: Weights sit in high-bandwidth memory right next to the compute, with on-chip streaming, so the model can keep evolving.

Specifications

Core model
Up to Qwen 3.5 35B
Decode speed
15,000 token/s (design target)
System power
70 W design target
Route
Near-memory compute
Model updates
Weights in external memory, can keep iterating
Process
SMIC 28 nm
Package / interfaces
Per project
Development kit
Evaluation board, SDK and model mapping tools

Figures on this page are current product definitions and design targets. Final specifications, test conditions, availability and delivery versions are confirmed in project documents agreed by both parties.

Chips in a tray next to a vacuum pick-up pen
Fig. 2 · Chips in a tray next to a vacuum pick-up pen

Typical applications

  • Embodied robots
  • Industrial edge servers
  • Air-gapped and secure terminals

Inference runs locally and data is processed on the device; it works fully offline.

Qwen3.5 → 3.6 → 3.8

Newer Qwen models, no new architecture.

Qwen3.6 and Qwen3.8 keep the Qwen3.5 hybrid layout, which Fanshi inference cores already map. A newer model in the same family is a new chip build, not a redesign.

From an email to a chip

  1. 01

    Pick the route

    Target model, performance and power goals, update cadence, interfaces. The first question is always: how often does the model change?

  2. 02

    Evaluate

    Run the model on the evaluation board, measure accuracy and throughput, and get a working engineering sample before any silicon is committed.

  3. 03

    Design in

    Interfaces, system software and field validation built around the evaluation results, turning the sample into a product prototype.

  4. 04

    Deliver the ASIC

    Once the model is frozen: a production chip, or the IP integrated into your own silicon.

Ask about Trident

Send the target model, performance and power goals, interfaces and timeline. We reply with a fit assessment and an evaluation plan.

Request an evaluation kit