AXE Specialists
Collection
Fine-tuned models, each purpose-built for a specific lane in the inference pipeline. • 7 items • Updated
Pegasus 1.0
Pegasus shows its work. 12 billion parameters tuned for problems that require visible step-by-step thinking.
Other models give you the answer. Pegasus gives you the path it took to get there — which means you can audit it, correct it, and trust it when the stakes are high. Built for code architecture decisions, formal reasoning, and any problem where "trust me" is not an acceptable answer.
Model details
| Property | Value |
|---|---|
| Developer | AXE Technologies |
| Base | Gemma-3 12B |
| Parameters | 12B dense |
| Context | 16K tokens |
| Quantization | Q4_K_M (GGUF) |
| License | Apache 2.0 |
What it's tuned for
- Chain-of-thought reasoning with explicit intermediate steps
- Code architecture review where the trade-off analysis matters as much as the answer
- Mathematical reasoning with worked intermediate steps
- Security analysis where the reasoning trail is the audit trail
Usage
ollama pull axetechnologies/pegasus-1.0
The AXE family
Five models, each tuned for a different lane in the inference pipeline:
| Model | Lane | What it does |
|---|---|---|
| Casanova 1.2 | Agency | Tool-calling, multi-step workflows. 27B dense. |
| Geralt 1.3 | Reasoning at scale | 26B parameters of capability, 4B of inference cost. MoE. |
| Pegasus 1.0 | Visible work | Chain-of-thought you can audit. 12B dense. |
| Artemis 1.0 | Speed | Loads in seconds. 4B for edge hardware. |
| Caesar 1.0 | First principles | Our own training cycle. ~1B, end-to-end on our pipeline. |
About AXE Technologies
Canadian in-house AI infrastructure. Built on Apple Silicon. The models run on hardware you can audit — no cloud dependency, no third-party model in the data path.
Website: axetechnologies.ca