Skip to content

Who is putting LLMs inside devices?

The teams that come to us fall into six groups. Find the one closest to you and see which route and which chip it usually starts from.

Evaluation board and camera module
Fig. 1 · System bring-up starting from an evaluation board

01

Handheld and voice hardware

Translators, recorders, AI earbuds, toys. A complete language model within a watt or two, working offline, on a battery that lasts all day.

Usually starts with Forge and the MaskROM route

02

Automotive and robotics

Cabin voice, embodied robots. A larger model running locally, with stable latency and no dependence on a connection.

Usually starts with Trident and near-memory compute

03

Industrial vision and inspection

Defect segmentation on the line, drone inspection, multi-sensor fusion. Keeping up with every frame while the data stays on site.

Usually starts with Argus and SRAM compute-in-memory

04

Air-gapped and secure terminals

Isolated networks in government, healthcare, energy and finance. Data must not leave the device, as a matter of architecture.

Every route runs locally; the model size picks the route

05

Chip teams with their own SoC

You have a chip, or are planning one, and want to add LLM inference without building an accelerator from scratch.

Usually starts with inference core IP and an FPGA evaluation board

06

Model companies and solution providers

You have a frozen or fine-tuned model, volume is growing, and API and GPU bills no longer make sense.

A chip built around your model

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.

What happens after you write

  1. 01

    Intro and NDA

    A short call about the project. Once a mutual NDA is in place, we share detailed specifications and evaluation material.

  2. 02

    Technical workshop

    We go through your workload together: target model, typical and maximum prompt lengths, single-shot versus multi-turn or agentic use, concurrency, and power and form-factor constraints.

  3. 03

    Feasibility report

    Proposed specifications, development milestones and indicative commercial terms, including NRE and unit pricing.

  4. 04

    Evaluate and build

    Hands-on evaluation with an evaluation kit, then an existing chip or a custom build for your model.

Not quite any of these?

Describe your model, device and volume in two minutes, and we will reply about your project specifically.

Describe your project