license: mit
🧠 Nexora-Qwen-Coder-4B
Compact Agentic Coding Model
Coding · Debugging · Tool Use · Structured Reasoning · Local AI
Nexora-Qwen-Coder-4B is a compact, coding-focused language model fine-tuned from the Qwen 3.5 4B family , with an emphasis on code generation, debugging, structured reasoning, tool use, and local agentic workflows .
The core idea behind Nexora is simple:
A small coding model should do more than generate code. It should understand the task, reason through problems, interact with tools, inspect feedback, and iterate toward a solution.
Designed for developers who want capable AI assistance without requiring a large datacenter-scale deployment.
✦ Model Overview
Property Details Model Nexora-Qwen-Coder-4BHugging Face guell00/Nexora-Qwen-Coder-4BBase Model Qwen 3.5 4B Architecture Dense Transformer Model Class 4B Parameters Primary Focus Coding & Agentic Workflows Fine-Tuning Nexora Fine-Tuning Training Method SFT + Curriculum Learning Reasoning Data Trace Inversion Agent Data Tool-Use & Agent Trajectories Training Context Up to 32K tokens Evaluation MTP, n=2 Format GGUF Inference llama.cpp compatible
⚡ Why Nexora?
Nexora-Qwen-Coder-4B is not designed around parameter count alone.
The objective is to make a compact local model more useful for real software development workflows .
The fine-tuning strategy focuses on four primary capabilities:
01 · CodingGenerate, complete, explain, refactor, and implement code across common programming tasks.
02 · DebuggingAnalyze errors, identify potential failure points, reason about bugs, and produce targeted fixes.
03 · Agentic WorkflowsOperate in environments where the model can inspect files, select tools, execute actions, receive feedback, and iterate.
04 · Structured ReasoningHandle multi-step technical tasks that benefit from planning, decomposition, and structured problem solving.
🎛️ Recommended Sampling
For the best balance of consistency, coding quality, and controlled generation , the recommended default configuration is:
Parameter Recommended Temperature 0.1Top P 0.95Top K 52Min P 0.05Repetition Penalty 1.1Presence Penalty Off
Default Configuration
1 Temperature: 0.1
2 Top P: 0.95
3 Top K: 52
4 Min P: 0.05
5 Repetition Penalty: 1.1
6 Presence Penalty: Off
This configuration is recommended for:
Code generation
Code completion
Debugging
Refactoring
Technical reasoning
Tool calling
Agentic coding workflows
The low Temperature is intended to improve consistency while preserving a small amount of generation flexibility.
Note: Evaluation results may vary when using sampling parameters different from those used during benchmarking.
📊 Benchmark Performance
Nexora-Qwen-Coder-4B was evaluated locally using the benchlocal evaluation framework.
The evaluation focuses primarily on practical developer workflows, including debugging, tool use, agent behavior, and instruction following.
Results
Benchmark Nexora-Qwen-Coder-4B Qwen 3.5 4B Delta BugFind-15 71 / 100 52 / 100 +19 HermesAgent-20 64 / 100 61 / 100 +3 ToolCall-15 100 / 100 90 / 100 +10 InstructFollow-15 93 / 100 93 / 100 0
Relative Evaluation Snapshot
1 BugFind-15
2 Nexora-Qwen-Coder-4B ██████████████░░░░░░ 71
3 Qwen 3.5 4B ██████████░░░░░░░░░░ 52
4
5 HermesAgent-20
6 Nexora-Qwen-Coder-4B █████████████░░░░░░░ 64
7 Qwen 3.5 4B ████████████░░░░░░░░ 61
8
9 ToolCall-15
10 Nexora-Qwen-Coder-4B ████████████████████ 100
11 Qwen 3.5 4B ██████████████████░░ 90
12
13 InstructFollow-15
14 Nexora-Qwen-Coder-4B ██████████████████░░ 93
15 Qwen 3.5 4B ██████████████████░░ 93
Key Observations
The strongest observed results were in:
Debugging Tool calling Coding-oriented workflows Instruction following Local agent scenarios
These results suggest that the fine-tuning process improved the model's performance on targeted coding and agentic tasks compared with the base evaluation reference.
Benchmark results are snapshots from specific evaluation runs. They should not be interpreted as universal performance guarantees.
🤖 Agentic Coding
Nexora-Qwen-Coder-4B is designed for workflows where the model can interact with an external environment rather than simply returning a single static answer.
A typical agent loop can be represented as:
1 ┌──────────────────┐
2 │ User Request │
3 └────────┬─────────┘
4 │
5 ▼
6 ┌──────────────────┐
7 │ Understand Task │
8 └────────┬─────────┘
9 │
10 ▼
11 ┌──────────────────┐
12 │ Plan Solution │
13 └────────┬─────────┘
14 │
15 ▼
16 ┌──────────────────┐
17 │ Select Tool │
18 └────────┬─────────┘
19 │
20 ▼
21 ┌──────────────────┐
22 │ Execute Action │
23 └────────┬─────────┘
24 │
25 ▼
26 ┌──────────────────┐
27 │ Inspect Feedback │
28 └────────┬─────────┘
29 │
30 ▼
31 Success?
32 ╱ ╲
33 Yes No
34 │ │
35 ▼ │
36 ┌───────────┐ │
37 │ Final │ │
38 │ Answer │ │
39 └───────────┘ │
40 │
41 └──────► Iterate
This makes the model suitable for local environments that expose tools such as:
File operations
Terminal execution
Code search
Repository inspection
Build systems
Test runners
Linters
Debugging environments
Typical agent workflows may include:
Read → Plan → Act → Observe → Verify → RepairTool-call reliability depends on the application's prompt template, tool definitions, schema design, and execution environment.
🧩 Recommended Use Cases
Use Case Fit Code Generation ★★★★★ Debugging ★★★★★ Tool Calling ★★★★★ Local Coding Agents ★★★★★ Code Explanation ★★★★★ Refactoring ★★★★☆ Repository Analysis ★★★★☆ Technical Reasoning ★★★★☆ Documentation ★★★★☆ Software Architecture ★★★☆☆
Best suited for
Code generation
Code completion
Debugging
Bug localization
Error analysis
Refactoring
Repository inspection
Tool calling
Local coding agents
Multi-step development tasks
Technical reasoning
Developer assistants
🖥️ Built for Local AI
The 4B parameter class is intentionally compact.
Nexora-Qwen-Coder-4B aims to provide a practical balance between:
1 CAPABILITY
2 ▲
3 │
4 │ ● Nexora-Qwen-Coder-4B
5 │
6 │
7 │
8 └────────────────────────►
9 LOCAL EFFICIENCY
The goal is straightforward:
Deliver useful coding and agentic capabilities while remaining practical to run locally.
Potential deployment scenarios include:
Local development
Personal coding assistants
Offline workflows
Lightweight coding agents
Developer workstations
Experimental AI agents
Privacy-focused development environments
📦 Model Files & Quantization
Nexora-Qwen-Coder-4B is available in GGUF format for efficient local inference.
Quantization Recommended For Q4_K_M Best balance of quality, memory, and speed Q8_0 Higher quantized quality with increased memory usage
Recommended: Q4_K_M
For most users, Q4_K_M provides a strong balance between:
Quality · Memory · Speed
Higher Quality: Q8_0
Recommended when memory usage is less restrictive and higher quantized fidelity is preferred.
🚀 Quick Start
llama.cpp
Run the model directly from Hugging Face:
llama-cli -hf guell00/Nexora-Qwen-Coder-4B --jinjaStart an OpenAI-compatible local server:
llama-server -hf guell00/Nexora-Qwen-Coder-4B --jinja
Command availability may depend on your installed llama.cpp version and the model files available in the repository.
🧠 Context Length
The model was fine-tuned using sequences reaching approximately 32K tokens .
The underlying Qwen 3.5 family may support larger context windows depending on the specific architecture and inference backend.
Long-context performance depends on:
Backend support
RoPE configuration
YaRN scaling
Quantization
KV cache
Available memory
Context length
When extending beyond the training distribution, users should validate performance on their own workloads.
Example: Extended Context with llama.cpp
1 ./llama-server \
2 -m model.gguf \
3 --ctx-size 131072 \
4 --rope-scaling yarn \
5 --rope-scale 4 \
6 --yarn-orig-ctx 32768
Important: Increasing --ctx-size alone does not guarantee reliable long-context behavior.
🎯 Deterministic Coding Configuration
For highly deterministic coding, debugging, and code-repair workflows:
Parameter Value Temperature 0Top P 0.95Top K 40Min P 0.05Repetition Penalty 1.1Presence Penalty OffMax Tokens Max
1 Temperature: 0
2 Top P: 0.95
3 Top K: 40
4 Min P: 0.05
5 Repetition Penalty: 1.1
6 Presence Penalty: Off
7 Max Tokens: Max
For creative programming, brainstorming, or exploratory generation, increasing the temperature may produce more diverse outputs.
For debugging and code repair, lower temperatures generally provide more deterministic results.
🔧 Built With
Technology Role Qwen Base model family Unsloth Fine-tuning & conversion workflows GGUF Efficient local model format llama.cpp Local inference benchlocal Coding & agent evaluation
⚠️ Limitations
Nexora-Qwen-Coder-4B is a compact 4B-class model and should be evaluated accordingly.
It may struggle with:
Extremely large repository-wide changes
Complex multi-file dependencies
Highly specialized professional domains
Tasks requiring extensive external knowledge
Long autonomous workflows without verification
Deep architectural decisions involving large systems
The model should be treated as a coding assistant , not a fully autonomous software engineer.
Generated code should always be:
1 REVIEWED
2 ↓
3 TESTED
4 ↓
5 VALIDATED
6 ↓
7 DEPLOYED
Applications should verify generated code before using it in production environments.
Depending on the inference template and runtime configuration, the model may generate reasoning content inside:
Applications may parse, hide, or otherwise handle these sections according to their requirements.
🙏 Acknowledgements
Special thanks to:
The Qwen team for the base model family.
The Unsloth team for efficient fine-tuning and conversion tooling.
The open-source AI community for datasets, tools, and research.
Contributors supporting local hardware testing and evaluation.
📜 License
This model is released under the MIT License .
Please review the licensing terms of the underlying base model and any third-party components used in your deployment.
⚖️ Disclaimer
Nexora-Qwen-Coder-4B is provided for:
Research · Development · Experimentation · Local Inference
Actual performance may vary depending on:
Quantization method
Inference backend
Hardware
Context length
Prompt formatting
Sampling parameters
Evaluation methodology
Benchmark results represent specific evaluation runs and should not be interpreted as guaranteed performance across all environments or tasks.
Always review, test, and validate generated code before deploying it to production systems.
🧠 Nexora
Intelligence. Code. Evolve.
Built for developers who want capable AI coding assistance running locally.
guell00/Nexora-Qwen-Coder-4B
