prithivMLmods/Nexus-9B-CodeCore-Merge-GGUF overview
Nexus 9B CodeCore Merge GGUF Nexus 9B CodeCore Merge is a merged 9B parameter coding and reasoning model designed for long horizon coding tasks, agentic coding…
Runs locally from ~4.31 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Nexus-9B-CodeCore-Merge.BF16.gguf | GGUF | GGUF | 16.69 GB | Download |
| Nexus-9B-CodeCore-Merge.Q3_K_L.gguf | GGUF | GGUF | 4.59 GB | Download |
| Nexus-9B-CodeCore-Merge.Q3_K_M.gguf | GGUF | GGUF | 4.31 GB | Download |
| Nexus-9B-CodeCore-Merge.Q4_K_M.gguf | GGUF | GGUF | 5.24 GB | Download |
| Nexus-9B-CodeCore-Merge.Q4_K_S.gguf | GGUF | GGUF | 4.98 GB | Download |
| Nexus-9B-CodeCore-Merge.Q5_K_M.gguf | GGUF | GGUF | 6.02 GB | Download |
| Nexus-9B-CodeCore-Merge.Q5_K_S.gguf | GGUF | GGUF | 5.87 GB | Download |
| Nexus-9B-CodeCore-Merge.Q6_K.gguf | GGUF | GGUF | 6.85 GB | Download |
Model Details
| Model ID | prithivMLmods/Nexus-9B-CodeCore-Merge-GGUF |
|---|---|
| Author | prithivMLmods |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | prithivMLmods/Nexus-9B-CodeCore-Merge |
| Last modified | 2026-09-21T07:27:59.000Z |
Model README
---
license: apache-2.0
base_model:
- prithivMLmods/Nexus-9B-CodeCore-Merge
tags:
- text-generation-inference
- llama-cpp
- omnimergekit
- qwen3_5
- reasoning
- chain-of-thought
- sft
- agent
- tool-use
- function-calling
- coder
language:
- en
pipeline_tag: text-generation
library_name: transformers
---
Nexus-9B-CodeCore-Merge-GGUF
> Nexus-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 NeoHorse-1-9B, OmniCoder-9B, 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 | Description |
|-----------|------------|-----------|-----------|-------------|
| Nexus-9B-CodeCore-Merge.BF16.gguf | BF16 | 17.9 GB | Link | Full BF16 weights. Highest quality, largest file size. |
| Nexus-9B-CodeCore-Merge.Q3_K_L.gguf | Q3_K_L | 4.93 GB | Link | Lower quality but usable, good for low RAM availability. |
| Nexus-9B-CodeCore-Merge.Q3_K_M.gguf | Q3_K_M | 4.62 GB | Link | Low quality. |
| Nexus-9B-CodeCore-Merge.Q4_K_M.gguf | Q4_K_M | 5.63 GB | Link | Good quality, default size for most use cases, recommended. |
| Nexus-9B-CodeCore-Merge.Q4_K_S.gguf | Q4_K_S | 5.35 GB | Link | Slightly lower quality with more space savings, recommended. |
| Nexus-9B-CodeCore-Merge.Q5_K_M.gguf | Q5_K_M | 6.47 GB | Link | High quality, recommended. |
| Nexus-9B-CodeCore-Merge.Q5_K_S.gguf | Q5_K_S | 6.31 GB | Link | High quality, recommended. |
| Nexus-9B-CodeCore-Merge.Q6_K.gguf | Q6_K | 7.36 GB | Link | Very high quality, near perfect, recommended. |
llama.cpp
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp
Run prithivMLmods/Nexus-9B-CodeCore-Merge-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models