---
license: apache-2.0
base_model:
- Qwen/Qwen3.5-9B
- OrionLLM/OxCoder-9B
- Jackrong/Qwopus3.5-9B-Coder
- ornith-ai/Ornith-1.5-9B
tags:
- text-generation-inference
- pytorch
- omnimergekit
- merge
- qwen3_5
- reasoning
- chain-of-thought
- sft
- agent
- tool-use
- function-calling
- coder
language:
- en
pipeline_tag: text-generation
library_name: transformers
---

# **Zenith-9B-CodeCore-Merge**

> Zenith-9B-CodeCore-Merge is a merged 9B-parameter coding and reasoning model designed for long-horizon coding tasks, agentic coding, and agentic reasoning. It is built by merging [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) as the base model with [OxCoder-9B](https://huggingface.co/OrionLLM/OxCoder-9B), [Qwopus3.5-9B-Coder](https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder), and [Ornith-1.5-9B](https://huggingface.co/ornith-ai/Ornith-1.5-9B), combining their capabilities for code generation, multi-step problem solving, instruction following, and autonomous coding workflows. The model is intended for complex software-engineering tasks that require sustained reasoning across multiple steps, code understanding, modification, debugging, and tool-oriented agentic workflows. This model is experimental and may generate artifacts.

- *GGUF: [Zenith-9B-CodeCore-Merge-GGUF](https://huggingface.co/prithivMLmods/Zenith-9B-CodeCore-Merge-GGUF). Note: The Multi-Token Prediction (MTP) heads are not preserved in this format. The model runs as a standard single-token-per-step autoregressive decoder.*

## Merge Recipe

```
hf download OrionLLM/OxCoder-9B \
  --local-dir ./models/OxCoder-9B

hf download Jackrong/Qwopus3.5-9B-Coder \
  --local-dir ./models/Qwopus3.5-9B-Coder

hf download ornith-ai/Ornith-1.5-9B \
  --local-dir ./models/Ornith-1.5-9B

hf download Qwen/Qwen3.5-9B \
  --local-dir ./models/Qwen3.5-9B
```

```
python omnimergekit.py \
  --base      models/Qwen3.5-9B --task-base ./models/Qwen3.5-9B \
  --source    models/OxCoder-9B \
  --source    models/Qwopus3.5-9B-Coder \
  --source    models/Ornith-1.5-9B \
  --weights   0.55,0.30,0.15 \
  --method omnimerge_v2 --density 0.53 --darex-q 0.75 --seed 42 \
  --no-auto-mlp-skip --skip-patterns visual.,mtp. \
  --output prithivMLmods/Zenith-9B-CodeCore-Merge
```

## omnimergekit

Tools for model merging, expert pruning, differential competence-map extraction, and GGUF quantization — https://github.com/mann1x/omnimergekit