APEXMTPVisionMIT

# Ornith-1.0-35B-MTP-APEX

English \| [📖 中文文档](https://huggingface.co/SC117/Ornith-1.0-35B-MTP-APEX-GGUF/blob/main/README_zh.md)

Self-improving agentic coding model · APEX quantized GGUFs + BF16 + mmproj

🐦 About Ornith

[Ornith-1.0-35B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B) is a self-improving agentic coding model from [DeepReinforce AI](https://deep-reinforce.com/ornith.html), post-trained on top of Qwen3.5 with RL to jointly optimize scaffold generation and solution rollouts.

It achieves state-of-the-art performance among open-source models of comparable size on Terminal-Bench 2.1, SWE-Bench Verified/Pro/Multilingual, NL2Repo, and OpenClaw.

This GGUF package includes the **mmproj-F16.gguf** vision projector for multimodal (image + text) capabilities with llama.cpp. MTP layers are sourced from Qwen3.5-35B-A3B (same architecture, compatible weights). **License: MIT.**

🧠 Model Details

|     |     |
| --- | --- |
| Architecture | Qwen3.5 MoE (Mixture of Experts) |
| Parameters | 35B total, 3B active per token |
| Experts | 256 routed experts, 8 active per token |
| Layers | 40 transformer layers + 1 MTP layer |
| Context | 262,144 tokens |
| MTP | 1 MTP layer (785 tensors) from Qwen3.5-35B-A3B |
| License | MIT |

📊 BenchLocal Results (APEX-I-Compact, 15.85 GB)

| Mode | ToolCall-15 | BugFind-15 | HermesAgent-20 | Max | Eff. |
| --- | --- | --- | --- | --- | --- |
| Thinking | 100 | 93 | 89 | 93.5 | 75.5 |
| No Thinking | 100 | 92 | 89 | 93.2 | 85.2 |

RTX 5070 Ti · No-thinking mode achieves better practical reliability (fewer retries).

🚀 Usage

llama.cpp (text only)

hf download SC117/Ornith-1.0-35B-MTP-APEX-GGUF --include "\*.gguf" --local-dir ./models
./llama-server -m ./models/Ornith-1.0-35B-MTP-APEX-I-Compact.gguf -ngl 99 -c 131072

llama.cpp (vision + text)

./llama-server -m ./models/Ornith-1.0-35B-MTP-APEX-I-Compact.gguf --mmproj ./models/mmproj-F16.gguf -ngl 99 -c 131072

🎛️ Recommended Settings

| Mode | Parameters |
| --- | --- |
| General | temperature=0.6, top\_p=0.95, top\_k=20 |
| Coding | temperature=0.6, top\_p=0.95, top\_k=20 |

💡 What is APEX?

These GGUF files are quantized using [APEX](https://github.com/mudler/apex-quant), an MoE-aware mixed-precision quantization technique. APEX classifies every tensor by its role — routed expert, shared expert, or attention — and applies a layer-wise precision gradient, giving sensitive edge layers higher precision and compressing redundant middle layers more aggressively.

APEX beats Q8\_0 perplexity at half the size — and even beats F16.

📦 APEX Quantization Tiers

| File | Size | Profile | Best For |
| --- | --- | --- | --- |
| `*-APEX-I-Quality.gguf` | 21.90 GB | I-Quality | Highest quality, best accuracy |
| `*-APEX-I-Balanced.gguf` | 24.18 GB | I-Balanced | Best all-rounder, recommended |
| `*-APEX-I-Compact.gguf` | 15.85 GB | I-Compact | Best quality/size ratio |
| `*-APEX-I-Mini.gguf` | 13.35 GB | I-Mini | Most compact, fits in 16GB VRAM |

## Links

- **Original Model**: [https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B)
- **Ornith Blog**: [https://deep-reinforce.com/ornith.html](https://deep-reinforce.com/ornith.html)
- **APEX Quantization**: [https://github.com/mudler/apex-quant](https://github.com/mudler/apex-quant)
- **BenchLocal Results**: [https://scorp1o117.github.io/benchlocal-results/](https://scorp1o117.github.io/benchlocal-results/)

## Citation

```bibtex
@misc{ornith-35b,
    title = {{Ornith-1.0-35B}: Agentic Coding, Open to All},
    url = {https://deep-reinforce.com/ornith_1_0.html},
    author = {{DeepReinforce Team}},
    year = {2026}
}
```

Downloads last month19,279

GGUF

Model size

0.4B params

Architecture

clip

Hardware compatibility

[Log In](https://huggingface.co/login) to add your hardware

16-bit

MTPBF16

71.1 GB

[View +4 variants](https://huggingface.co/SC117/Ornith-1.0-35B-MTP-APEX-GGUF/tree/main)

Inference Providers [NEW](https://huggingface.co/docs/inference-providers)

[Text Generation](https://huggingface.co/tasks/text-generation "Learn more about text-generation")

This model isn't deployed by any Inference Provider. [🙋Ask for provider support](https://huggingface.co/spaces/huggingface/InferenceSupport/discussions/new?title=SC117/Ornith-1.0-35B-MTP-APEX-GGUF&description=React%20to%20this%20comment%20with%20an%20emoji%20to%20vote%20for%20%5BSC117%2FOrnith-1.0-35B-MTP-APEX-GGUF%5D(%2FSC117%2FOrnith-1.0-35B-MTP-APEX-GGUF)%20to%20be%20supported%20by%20Inference%20Providers.%0A%0A(optional)%20Which%20providers%20are%20you%20interested%20in%3F%20(Novita%2C%20Hyperbolic%2C%20Together%E2%80%A6)%0A)

## Model tree for SC117/Ornith-1.0-35B-MTP-APEX-GGUF

Base model

[deepreinforce-ai/Ornith-1.0-35B](https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B)

Quantized

( [108](https://huggingface.co/models?other=base_model:quantized:deepreinforce-ai/Ornith-1.0-35B))

this model

## Collection including SC117/Ornith-1.0-35B-MTP-APEX-GGUF

[a self-improving family of open-source models for agentic coding.•3 items•Updated 4 days ago• 2](https://huggingface.co/collections/SC117/ornith-10)