---
title: Ornith-1.0-9B-NPU2
canonical_url: "https://www.modelscope.ai/models/Atomic-Germ/Ornith-1.0-9B-NPU2"
md_url: "https://www.modelscope.ai/models/Atomic-Germ/Ornith-1.0-9B-NPU2.md"
repository: Atomic-Germ/Ornith-1.0-9B-NPU2
last_updated: 2026-08-21
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_5_text
architectures:
  - Qwen3_5ForConditionalGeneration
base_model:
  - ornith-ai/Ornith-1.0-9B
base_model_relation: quantized
downloads: 0
stars: 0
tags:
  - qwen3_5
  - image-text-to-text
  - text-generation
  - conversational
  - eval-results
  - flm
  - fastflowlm
  - q4nx
  - npu2
---

# Ornith-1.0-9B-NPU2

> Ornith-1.0-9B-NPU2 - An open-source model by Atomic-Germ on ModelScope. Coding-focused

Atomic-Germ/Ornith-1.0-9B-NPU2 is a image-text-to-text model on ModelScope. licensed under mit. derived from ornith-ai/Ornith-1.0-9B.

- **Repository**: Atomic-Germ/Ornith-1.0-9B-NPU2
- **License**: mit
- **Tasks**: image-text-to-text
- **Base model**: ornith-ai/Ornith-1.0-9B
- **Tags**: qwen3_5, image-text-to-text, text-generation, conversational, eval-results, flm, fastflowlm, q4nx, npu2
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-08-21

Source: https://www.modelscope.ai/models/Atomic-Germ/Ornith-1.0-9B-NPU2

---

# *IF YOU USE COMMUNITY QWEN MODELS DO NOT UPGRADE TO FLM v1.0.2+*

# Ornith-1.0-9B-NPU2

**FastFlowLM Q4NX conversion of [`ornith-ai/Ornith-1.0-9B`](https://huggingface.co/ornith-ai/Ornith-1.0-9B)** for AMD XDNA NPU inference.

This repository contains a quantized **Q4NX** port of the model, compiled for the FastFlowLM (FLM) runtime. It is **not** a GGUF file.

| Item | Value |
|------|-------|
| Source model | [`ornith-ai/Ornith-1.0-9B`](https://huggingface.co/ornith-ai/Ornith-1.0-9B) |
| Weights | `model.q4nx` (7.11 GB) |
| Modality | language / vision |
| FLM version | `1.0.2` |
| Converted | 2026-08-18 |

## Install and run

This repository works with `flm-add`, a small installer that copies the model
into the FastFlowLM user directory and registers the tag. It never
modifies the system FastFlowLM install.

`pip install flm-add` or `uv tool install flm-add`

```bash
uv tool install flm-add
flm-add --modelscope Atomic-Germ/Ornith-1.0-9B-NPU2 --family qwen3.5
FLM_CONFIG_PATH="$HOME/.config/flm/model_list.json" FLM_XCLBIN_PATH="$HOME/.config/flm" flm run ornith:9b
```

## Files

| File | Description |
|------|-------------|
| `model.q4nx` | Quantized weights (Q8_0 / Q4_1 / BF16) |
| `config.json` | FLM runtime configuration |
| `tokenizer.json` | Tokenizer vocabulary |
| `tokenizer_config.json` | Tokenizer configuration |
| `chat_template.jinja` | Chat template |
| `vision_weight.q4nx` | Vision model |


---

## Source model card

See the original model card: [ornith-ai/Ornith-1.0-9B](https://huggingface.co/ornith-ai/Ornith-1.0-9B)