SHT 1 / 5 — GLEBEFISH LIMITED

Glebefish

AI consultancy for companies building real products — where software, firmware, and hardware meet intelligence.

Start a briefSouth of England · info@glebefish.com
SHT 2 / 5 — LIVE FROM THE BENCH

Running now, in our lab

The numbers below come from a production multi-device AI system running in our own lab — local language models, device coordination, and voice control across a mesh of consumer-grade hardware. It is the kind of system we build for clients, measured rather than described.

Mesh nodes
4
Raspberry Pi coordinator, x86 iGPU inference node, Windows controller node, networked audio endpoint
Inference hardware
AMD Ryzen 8845HS / Radeon 780M iGPU · 16 GB shared memory · 65 W-class mini-PC
Measured decode throughput
llama3.2:3b36.7 tok/s
qwen3:4b30.1 tok/s
deepseek-r1:8b17 tok/s
qwen3:8b16.6 tok/s

LAST MEASURED 15 JULY 2026

SHT 3 / 5 — CAPABILITIES

What we take on

AI strategy for hardware companies

You build a physical product and the board wants AI in it. We turn that into a costed, buildable roadmap — including the honest answer when the right amount of AI is less than expected.

grounded in shipping firmware, not slideware

Embedded & edge AI

Language models, classification, and decision-making running on the device itself — no cloud round-trip, no per-query bill, no customer data leaving the product.

see SHT 2 — those are our own measurements

Firmware + AI integration

The unglamorous part most AI consultancies can't do: making intelligence coexist with real-time constraints, watchdogs, OTA updates, and the rest of an embedded stack.

electronics, firmware & software design background

Predictive analytics for manufacturing

Condition monitoring, anomaly detection, and process optimisation from the sensor data your line already produces.

R&D experience across consumer & industrial products

Computer vision for devices & automation

Inspection, counting, presence, and safety applications — scoped to run on hardware that matches the budget of the product it ships in.

edge-first: the camera and the model share a box

Model selection & evaluation

Which model, at which size, on which hardware — answered with benchmarks rather than vendor claims. The right model is often smaller and cheaper than the default choice.

we rank models by measured task performance

Where the experience comes from

Kenwood / De'LonghiBritish American TobaccoGEElliot ScientificOhme

electronics, firmware & software design roles — preceded by 20 years in contract R&D

SHT 4 / 5 — START A BRIEF

Describe the problem. Watch it become a brief.

Write it the way you'd explain it to a colleague — our assistant structures it into a scoped brief on the spot, before you decide whether to send it.

BRIEF — AWAITING INPUT

Company
Glebefish Limited
Location
South of England