Zenith-9B-CodeCore-Merge-GGUF
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 as the base model with OxCoder-9B, Qwopus3.5-9B-Coder, and 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.
Model Files
| File Name | Quant Type | File Size | File Link |
|---|---|---|---|
| Zenith-9B-CodeCore-Merge.BF16.gguf | BF16 | 17.9 GB | Download |
| Zenith-9B-CodeCore-Merge.Q3_K_L.gguf | Q3_K_L | 4.93 GB | Download |
| Zenith-9B-CodeCore-Merge.Q3_K_M.gguf | Q3_K_M | 4.62 GB | Download |
| Zenith-9B-CodeCore-Merge.Q4_K_M.gguf | Q4_K_M | 5.63 GB | Download |
| Zenith-9B-CodeCore-Merge.Q4_K_S.gguf | Q4_K_S | 5.35 GB | Download |
| Zenith-9B-CodeCore-Merge.Q5_K_M.gguf | Q5_K_M | 6.47 GB | Download |
| Zenith-9B-CodeCore-Merge.Q5_K_S.gguf | Q5_K_S | 6.31 GB | Download |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp