Balsa Omni

Balsa Omni v1 is a multimodal model for the UK, with 4.5B effective parameters. It reads text, images and audio, replies in British English and runs on device, with no cloud.

Benchmarks

Tested on banking
and support prompts.

Share of test prompts passedHigher is better · %
4Base model
4%
100Balsa Omni v1
100%
Honest answers on payment status45 prompts
72Base model
72%
100Balsa Omni v1
100%
Refuses, then gives a safe next step36 prompts
80Base model
80%
100Balsa Omni v1
100%
Ends support chats with a next step20 prompts
0Base model
0%
100Balsa Omni v1
100%
Writes amounts in pounds (£)24 prompts
0Base model
0%
100Balsa Omni v1
100%
Writes dates in the UK format8 prompts
60Base model
60%
100Balsa Omni v1
100%
Uses British spelling in replies15 prompts
Every check, in detail15 checks
CheckBase modelBalsa Omni v1v1 against base
Amounts in poundsWrites amounts with the £ sign0%100%+100 pts
UK date formatWrites dates the UK way0%100%+100 pts
Payment status answerSays it cannot see accounts, then gives a next step4%100%+96 pts
Payment status, looser ruleThe same status check with a looser pass rule20%100%+80 pts
British spellingUses UK spelling, such as organise60%100%+40 pts
Refuses and gives a safe stepRefuses, then points to a safe way to get help72%100%+28 pts
Gives a next step in chatsEnds with something the customer can do80%100%+20 pts
Refuses PIN, password and code requestsWill not reveal a PIN, password or code94%100%+6 pts
British spelling in chatsKeeps UK spelling in longer chats95%100%+5 pts
Keeps its instructions privateWill not repeat its own setup instructions100%100%=
Answers ordinary banking questionsAnswers normal questions instead of refusing100%100%=
Does not claim to check an accountDoes not say it will look into an account100%100%=
Uses only amounts the customer gaveUses only amounts the customer gave100%100%=
General questionsAnswers general knowledge questions in the asked format97%93%-4 pts
Banking answer has the key factsThe answer holds the facts the customer needs100%87%-13 pts

The base model is an open model, run with no prompt. Balsa Omni v1 adds our banking prompt and our tuning. With the same prompt on both, the tuning alone raises payment status from 62% to 100% and next step in chats from 70% to 100%. Each check is a pass-or-fail rule on one reply, over 214 text prompts written for a UK bank support chat, on the same machine. How we test

Capabilities

One model,
four jobs done well.

Fraud defence

Refuses requests for a PIN, password or code. Then it points the customer to a safe way to get help.

100% refusal with a safe step

Honest payment status

Says plainly that it cannot see the account. It invents no status or amount and gives a real next step.

100% payment status answers

Written for the UK

British spelling, amounts in pounds and UK dates, in every test prompt.

100% amounts in pounds

Text, image and audio

Reads text, images and audio, and answers in text. It has 4.5B effective parameters in 4-bit weights and runs on a 16 GB Mac, with no cloud.

2.50 s mean reply
Model card

4.5B effective parameters.
On device, no cloud.

Balsa Omni

A 4.5B multimodal model for the UK that writes British English. Its first tuned job is UK banking support, on device.

Built for
The UK
Built on
An open model (Apache 2.0)
Base model languages
Pre-trained on 140+ languages, supports 35+ out of the box, as published by its maker
Domain
General use, in British English. Tuned and tested for UK banking support.
Version
v1, November 2026
Spec
Model
balsa-omni-4b-v1
Parameters
4.5B effective, 8B with embeddings
Context window
128K tokens
Weights
4-bit, MLX
Tested system RAM
16 GB
Peak model memory
Not measured yet
Language
British English
Input
Text, image, audio
Output
Text
Runs on
Apple silicon, on device
Mean time per reply
2.50s

Mean time per reply on one 16 GB Apple silicon Mac.

Repeatability
21/21

Re-run prompts gave the same reply, word for word.

Built for the UK
  • British spelling100%
  • Amounts in pounds100%
  • UK date format100%
  • Keeps its instructions private100%
Film

Watch it run
on device.

How it answers.

  1. 01Ask
  2. 02Read the context
  3. 03Answer
  4. 04Stream as it writes
Playground

Try it yourself.
Watch it work, step by step.

Pick a step or let it play. Every run shows how long it took on the machine itself.

Balsa Omnibalsa-omni-4b-v1 · 4-bitRecorded run
Try another
Questions

Asked often.

Balsa Omni v1 is a multimodal model for the UK, with 4.5B effective parameters. It reads text, images and audio, replies in British English, and its first tuned job is UK banking support.

Balsa Omni v1 is our fine-tuned derivative of an open model, under the Apache 2.0 licence. We tuned it for British English and UK banking support.

Balsa Omni v1 takes text, images and audio as input and answers in text. The benchmark on this page scores text chat.

No. Balsa Omni v1 runs on device, so customer data stays on your own machines.

Balsa Omni v1 has 4.5B effective parameters in 4-bit weights and runs on a 16 GB Apple silicon Mac. Its mean reply time is 2.50 s.

Balsa Omni v1 writes British English. It scored 100% on UK spelling, amounts in pounds and UK dates.

Balsa Omni v1 was tested on 214 text prompts for a UK bank support chat. Fixed rules scored each reply on 15 checks, against the base model on the same machine.

Write to research@f-r.co.

Balsa Omni

Want it on
your machines?