# Ornith 1.5 9B

> Canonical: https://www.overmindlab.ai/models/ornith-1-5-9b

9B Qwen 3.5 finetune with a 256K window and tool calling.

| Property | Value |
| --- | --- |
| Model ID | ornith-ai/Ornith-1.5-9B |
| Provider | Ornith |
| Group | Ornith |
| Parameters | 9B |
| Tier | Small |
| Context window | 256K |
| Max training context | 128K |
| Tool calling | Yes |
| Training methods | LoRA |
| Training cost | from $0.61 |
| Serving cost (per 1M output tokens) | from $6.00 |

## Overview

Same architecture as Qwen 3.5 9B: 8 full-attention layers, 256K positions, tool calling. LoRA uses the 128K window measured on that base.

Ornith 1.5 9B is a Qwen 3.5 9B finetune. It trains with LoRA on the Qwen 3.5 stack and serves on the pinned vLLM image with thinking disabled.

## Good for

- Agents that start from the Ornith 1.5 9B checkpoint
- LoRA on a 9B Qwen 3.5 architecture
- Tool-calling rows

Train this model on your agent's data: https://docs.overmindlab.ai/models/training.md

## Related models

- [Ornith 1.5 35B MoE](https://www.overmindlab.ai/models/ornith-1-5-35b-a3b): 35B MoE (3B active), 256K context