Compute partnership · August 2026

A 27B model that works in Tunisian Arabic: chat, translation, diacritisation, and writing in a style you hand it. It reads images and video as well. It was trained on text there is nowhere to buy.

أحنا نبنيو أول موديل يفهم التونسي كيما يحكيوه التوانسة، بالدارجة، بالفرنساوي، والكل مخلوط.“We're building the first model that understands Tunisian the way Tunisians actually speak it.”

What we can tell you today.

Family
Barca H1
Parameters
27B
Does
Chat, translation, diacritisation, style imitationall of it in Derja
Also reads
Images and videonot written up here yet
Does not do
Audio. Transcription is Fennec's
Decode
About 111 tokens a secondsingle stream
Quality benchmark
not yet
Licence
not yet
Status
Shipped

This page used to lead with a speech benchmark. That work is real and it is still published, on Fennec, which is the model that does the hearing and now scores better than the number that was here. What is left above is what has been measured about Hannibal itself. The two blank rows stay blank until somebody runs them.

The models are the fast part. The engine behind them was not.

One pipeline feeds the whole lineup: the text this model was trained on, and the audio behind the other two.

01 · Collect

Audio nobody is selling

Tunisian TV and creator channels, pulled apart by source separation, diarization and segmentation. Two thousand hours of native speech and 1.31 million segments, all of it ours, because there is nothing on the market to buy.

02 · Vote

Four labelers that have to agree

Two independent ASR lineages, a CTC mixer and a Kaldi system. A transcript only gets in when they converge. Then a Derja-native language model checks the text actually sounds Tunisian, and hard filters throw out anything Egyptian or Moroccan that slipped through.

03 · Anchor

Every gate calibrated on humans

1,700 human-verified clips set the thresholds and 98.4 fully verified hours anchor each run. The audio is the asset we keep forever. The labels are disposable, and every new model rewrites them better than the last one did.

2,000+ h

of Tunisian speech collected and processed

421M

tokens of validated Tunisian text, Arabic script, Tunizi and MSA

1.31M

segments through the pipeline so far

369k

clips being relabeled by the champion right now

The expensive part is already paid for.

The corpus is built and three models are serving on one API. The only input we do not have is hours. Six months from now this is obvious and expensive; today it is four weeks of one machine.

Put it in your product.

POST /api/v1/chat/completions · "model": "hannibal"

Hannibal has shipped: no waitlist, no access review. Sign in and create a key, shown once and stored hashed, and the first request is a copy-paste from the docs. Free while the beta lasts, 60 requests a minute.

No key yet? You can still talk to it in the playground.

Four weeks on a machine of our own.

All of this was built on a shared node, in the gaps between other people's reservations. Give us the machine and the same team runs this loop weekly.

4 weeks, 8×B200 class
The next generation of every model here, finished. Corpus-scale training, the synthetic flywheel, and the evaluation sweeps that are currently the queue.
What a generation costs
50 to 400 GPU-hours to train, about 150 for a labeling sweep. On a dedicated node the loop turns weekly instead of monthly.
What is already done
The corpus, the validation stack, and three models serving on one API. The only input we are missing is hours.
What you get
Your name on the reference language stack for 13 million Tunisian speakers, and a data engine that already works, pointed at whichever language you want next.

What you're about to ask.

Can Hannibal transcribe audio?

No. It reads and writes, and it can look at an image or a video, but it does not hear. Transcription is Fennec, on POST /api/v1/audio/transcriptions. Hannibal served that endpoint while Fennec was in training and a request naming it there is now refused, which is better than handing back another model's transcript under this one's name.

Where did the speech numbers on this page go?

To Fennec, which is the model they belong to. They also improved on the way: the figure this page used to lead with is superseded. The whole table is published there, including the columns we have not rerun.

What is measured about Hannibal itself?

Decode speed, at about 111 tokens a second on a single stream, which is what you need to decide whether to stream a reply or wait for it. There is no published quality benchmark for Derja chat, ours or anyone else's, and this page will not invent one. The spec table says so rather than leaving the row out.

What stops a big lab from doing this next quarter?

The data. There is no Tunisian corpus to license, at any price. We collected 2,000 hours of speech and 421M tokens of text, then built the four-voter labeling stack and the human calibration set that decide what is good enough to train on. A lab starting today starts at the beginning of the pipeline, not the beginning of the model.

Get an API key