basal-2.0 and basal-omni — text, images, audio. Your decision.

7 min read Original article ↗

pico 0.8B + engine 2.3.2

BASAL 2.0 + BASAL-OMNI

Decisions from text.
Now also
from images and audio.

basal-2.0 reads text. basal-omni also accepts images and recordings. You define the questions and allowed answers. The model chooses between them — locally, with a confidence estimate.

🇵🇱 Polish · 🇬🇧 EnglishOpen weights · Apache 2.0

FROM DATA TO ACTION local

Textemail · document · context

TEXT MODELSbasal-2.0

pico (0.8B) · mini (1.5B)
4.5B · max (11B)

Text Image Audio

MULTIMODAL MODELSbasal-omni

mini (4B) · max (12B)
ultra (31B)

ONE DECISION INTERFACEYour questions. Structured answers.

CategoryUrgencyNext action

System-1 models · a classifier defined with every request

01 / CHOOSE YOUR MODEL

Two families.
A shared language of decisions.

The same dynamic classifier concept. Choose text models for fast automation, or multimodal models when the answer is in an image or recording.

TEXTMain release

basal-2.0

Fast decisions in your workflow.

Messages, documents, RAG and an agent’s next tool. Up to 255 options per question and multiple questions about a shared context. mini, 4.5B and max are based on Bielik; pico on Qwen3.5.

Weights on Hugging Face: basal-2.0 collection · bf16, FP8, GGUF, MLX

pico: an 812 MB GGUF file, also runs on CPU. See the results and film →

NVIDIA GPU · Mac / MLX · Ollama / llama.cpp

Run a text model

TEXT + IMAGE + AUDIOExperimental

basal-omni1.0

Decisions from what you see and hear, too.

A document scan, a product photo, a recorded customer request. Send the media and ask about its content, without a separate OCR or transcription step. Foundation: Gemma 4.

Weights on Hugging Face: basal-omni-1.0 collection · bf16. New from Saturday 17 October, 09:00: ultra (31B, also FP8 for vLLM) and the experimental max 1.1, trained on the tasks of engine 2.1.

NVIDIA GPU · bf16 / eager · ok. 16 GB mini, 24 GB max, GPU 80 GB ultra

Run a multimodal model

basal-omni is our first release with media: images and audio use the base model's capabilities without additional multimodal training. Calibration comes from text. ultra reads text and images, not audio. Check results and limitations →

02 / HOW BASAL WORKS

The classifier changes
with your question.

You don't train a separate model for every list of categories. You describe them in the request. The next question can address an entirely different process.

01

Provide the data

Text for basal-2.0. Text, images or audio for basal-omni.

“The shipment arrived damaged”
02

Ask your questions

Which team? How urgent? Which topics? Several questions about one context in the same call.

Sales · Complaints · Logistics
03

Use the decision

Get the result and probabilities. Your application takes the next step or hands the case to a person.

Complaints → support queue

choice one optionnoul yes / noscore ratingmulti multiple labelsact action with coststool agent toolclassifyverifycompressextract tasks · basal 2.1All schemas ↗

IN PRACTICE

Where can you use basal?
Examples in brief.

Wherever the next step of a process depends on what a document, message or recording says. You describe the question and the allowed answers; the model returns a decision with a confidence level.

18 scenarios with sample API requests ↗
Film about calibrating a basal model on your own data

NEW FILM / 7:16 · PL / EN SUBTITLES

Your data. Your thresholds.
A measured decision.

The basal 2.2 engine step by step: labelled examples, a report without writing anything, certified thresholds fitted on your data, and the server with the new calibration file.

Watch the calibration film

An animated guide to typed decision models

FILM / 14:51 · PL / EN SUBTITLES

An intelligent IF / CASE.
Explained step by step.

From one message to a decision: dynamic classification, probabilities, costs and basal’s six question types.

See how a decision model works

Explainer film on every basal question schema

FILM / 15:59 · NAPISY PL / EN

Every question schema and the basal 2.1 tasks.
Explained step by step.

Every question type with a full JSON example: from choice, noul and score through multi, act and tool to SOAM, calibration and the classify, verify, compress and extract tasks.

Watch the film on schemas and tasks

Both families on the same text test.

Werdykt to nasz ukryty benchmark: 10 kategorii po polsku i angielsku. Pokazujemy sześć modeli basal oraz punkty odniesienia — model API, otwarty model, Jev 1.14, Liquid d1-ultra i Respan Span-02 w dwóch ustawieniach: z rozumowaniem i bez niego (jeden przebieg, jak basal).

5 000decisions · the same protocol

basal-2.0 focuses on speed and hardware flexibility. basal-omni also handles text; its ultra (31B) has the highest accuracy in the basal family.

These are text results. Image and audio quality are shown in the other tab.

See all systems ↗

ACCURACY · MEAN ACROSS 20 CELLSHIGHER IS BETTER ↗

Time and cost: shorter bars are better. Each scale runs from zero to the maximum in this comparison.

Werdykt measures text decisions. Full data and comparison conditions are on the benchmark page.

New: Codex + basal + Claude Code via MCPThree Herdr panes. Real decisions. A cost check before action.

The recordings show earlier model versions. Each case lists the version and actual measurements. Videos are in Polish. Open the use case catalog →

05 / START BUILDING

One engine.
Two model families.

Run basal-2.0 for text or basal-omni for images and audio. Both accept questions through POST /v1/systemone. Switch models, keep the same integration.

Python, TypeScript or plain HTTP n8n and your own applications Computation and data on your hardware

Current engine: basal 2.3.2. Pico support, GGUF fixes and hardware compatibility checks. Explore the inference server →

Full documentation
# 1. Create an environment (requires uv)
uv venv --python 3.12 --allow-existing ~/basal-env
source ~/basal-env/bin/activate

# 2. Install PyTorch and the engine
uv pip install torch==2.11.0 \
  --index-url https://download.pytorch.org/whl/cu128
uv pip install "basal[fp8] @ https://github.com/rkinas/basal/archive/refs/tags/v2.1.0.tar.gz"

# 3. Start the model (bf16; FP8 port: Remek/basal-2.0-4.5B-FP8 --mode fp8)
basal-serve --model Remek/basal-2.0-4.5B \
  --mode fast --template-prefix off --port 8000

TERMINAL · LINUX / WSL + NVIDIA GPUv2.1.0

Install uv and a driver supporting CUDA 12.8 (B300 and HP ZGX Nano (Nvidia DGX Spark): cu130). The first start compiles the model for a few minutes. All GPUs: hardware guide.

GOOD TO KNOW

Which basal
fits your project?

Text or multimodal?

Choose basal-2.0 for fast text decisions on GPU, Mac or through Ollama. Choose basal-omni for image or audio input. Omni also answers text questions, but currently runs only on NVIDIA GPUs in eager mode.

Does the model write answers like a chatbot?

By default, it returns a typed decision and probabilities for the allowed answers. Use a generative model to write an email or summary; basal can select a path, assess the input or check the result. The release article describes the experimental thinking mode in basal-2.0 4.5B.

What is new in basal 2.1?

Engine v2.1.0 adds four experimental tasks on the same API: classify (labels with a rubric each), verify (whether statements follow from the text), compress (the parts a question needs) and extract (JSON schema fields copied exactly from the document). The model does not write text: a task is built from its decisions. On Saturday 17 October basal-omni-1.0-ultra (31B) and the experimental task model basal-omni-1.1-max arrive. See the tasks →

Which media does basal-omni support?

Images and audio recordings up to 30 seconds, including alongside text in one request (ultra: images only). This release does not accept video files directly. Your application can extract frames and the audio track first.

Does data have to leave the company?

No. After downloading the weights, you run the model on your own hardware and control the application and its connections. Inference itself needs no external API.

What does the confidence level mean?

It is a calibrated model estimate, not a guarantee of correctness. Choose a threshold using examples from your own process. basal-omni uses calibration fitted on text; it needs separate validation on images and recordings. Explore calibration measurements →

LAUNCH / WEDNESDAY, 14 OCTOBER

Explore the full release.

basal-2.0 and basal-omni: models, results, calibration and practical API examples. All the details in one article.

Read about basal 2.0 and omni