---
license: mit
license_link: https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B/blob/main/LICENSE
thumbnail: https://huggingface.co/AtomicChat/ornith-9b-GGUF/resolve/main/hero.png
base_model:
- deepreinforce-ai/Ornith-1.0-9B
base_model_relation: quantized
quantized_by: AtomicChat
pipeline_tag: text-generation
library_name: gguf
tags:
- atomic-chat
- ornith
- deepreinforce-ai
- gguf
- llama.cpp
- quantized
---
**Ornith 1.0 9B**, self-quantized to GGUF by [Atomic Chat](https://atomic.chat). Built straight from DeepReinforce's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline.
## Highlights
- **0.0B parameters**: the weights this repo quantizes.
- **Context length**: 262,144 tokens (256K), as published by DeepReinforce.
- **32 layers**: Dense decoder.
- **Modalities**: the base model handles Text, Image; this repo ships text-only quants, it carries no vision projector.
- **Full imatrix ladder**: every quant is calibrated with an importance matrix.
- **State-of-the-Art Coding Agents**: Available in 9B-Dense, 31B-Dense, 35B-MoE, and 397B-MoE (post-trained on top of Gemma 4 and Qwen 3.5), achieving state-of-the-art performance among open-source models of comparable size on coding benchmarks such as Terminal-Bench 2.1, SWE-Bench, NL2Repo and OpenClaw.
- **Self-Improving Training Framework**: Ornith-1.0 employs RL to learn to generate not only solution rollouts, but also the scallfold that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model discovers better search trajectories and generates higher-quality solutions.
> [!NOTE]
> These GGUFs are **self-quantized from the original weights**, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.
> [!IMPORTANT]
> Always pass `--jinja` so the **Ornith 1.0 9B chat template** is applied. Without it the model can emit malformed turns.
## Model Overview
| Property | Value |
|---|---|
| Base model | `deepreinforce-ai/Ornith-1.0-9B` |
| Parameters | 0.0B |
| Layers | 32 |
| Context length | 262,144 tokens (256K) |
| Vocabulary | 248,320 |
| Modalities | Text, Image in the base model; text only in this repo, it ships no vision projector |
| Architecture | Dense decoder, 16 attention heads over 4 KV heads, `Qwen3_5ForConditionalGeneration` |
| This repo | GGUF quants (imatrix). Quants: `IQ4_XS`, `Q4_K_M`, `UD-Q4_K_XL`, `Q5_K_M`, `Q6_K`, `Q8_0` |
Scores are DeepReinforce's published results for the base `deepreinforce-ai/Ornith-1.0-9B`, not our own measurements. Quantization preserves the large majority of this; `Q4_K_M` and up stay close to full precision.
## Choosing a quant
| Quant | Size | Notes |
|---|---|---|
| `IQ4_XS` | 5.2 GB | Excellent quality for size. Recommended low-bit. |
| **`Q4_K_M`** | 5.6 GB | **Recommended default. Best balance of size, speed and quality.** |
| `UD-Q4_K_XL` | 6.4 GB | Dynamic. Embeddings and output kept at Q8_0 for higher quality at a Q4 footprint. |
| `Q5_K_M` | 6.5 GB | Higher quality, low loss. |
| `Q6_K` | 7.4 GB | Near lossless, noticeably lighter than Q8_0. |
| `Q8_0` | 9.5 GB | Effectively lossless, reference quality. |
> [!TIP]
> Pick the largest file that fits your (V)RAM with room for context. `Q4_K_M` or `UD-Q4_K_XL` is the sweet spot for most setups; `Q6_K` or `Q8_0` for maximum fidelity.
## Get started
Run Ornith 1.0 9B locally with:
- **[Atomic Chat](https://atomic.chat):** the easiest path. Open the app, search `AtomicChat/ornith-9b-GGUF`, pick a quant, hit **Use this model**.
- **llama.cpp:** `llama-server -hf AtomicChat/ornith-9b-GGUF:Q4_K_M --jinja -c 8192`
- **Ollama:** `ollama run hf.co/AtomicChat/ornith-9b-GGUF:Q4_K_M`
- **LM Studio / Jan:** search the repo id, download any quant.
## Best practices
| Parameter | Value |
|---|---|
| temperature | 1.0 |
| top_p | 1.0 |
| top_k | 20 |
DeepReinforce's recommended sampling configuration for `deepreinforce-ai/Ornith-1.0-9B`.
## Run in llama.cpp
```bash
git clone https://github.com/ggml-org/llama.cpp
cmake llama.cpp -B llama.cpp/build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --target llama-cli llama-server
```
```bash
./llama.cpp/build/bin/llama-server \
-hf AtomicChat/ornith-9b-GGUF:Q4_K_M \
--jinja -ngl 99 -c 8192 -fa on
```
## How these were made
1. Download `deepreinforce-ai/Ornith-1.0-9B` (original weights).
2. Convert to f16 GGUF with [llama.cpp](https://github.com/ggml-org/llama.cpp).
3. Build an importance matrix over our calibration corpus.
4. Quantize the ladder with `--imatrix`.
5. `UD-Q4_K_XL` additionally pins the token-embedding and output tensors to `Q8_0`.
## License
Original model by DeepReinforce, released under the MIT license. Full terms: [MIT](https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B/blob/main/LICENSE). Quantized by Atomic Chat.
