willhar/Qwen3.5-9B-AgentTuned-GGUF overview
Model Card for willhar/Qwen3.5 9B AgentTuned GGUF This model is meant to improve upon base Qwen 3.5 9B's tool calling, instruction following, and logical think…
Runs locally from ~17.14 GB disk (24 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.5-9B-AgentTuned-F16.gguf | GGUF | F16 | 17.14 GB | Download |
Model Details
Model README
---
datasets:
- NousResearch/hermes-function-calling-v1
- LiquidAI/ifstruct-v1.0
- paraloq/json_data_extraction
- DJLougen/hermes-agent-traces-filtered
base_model:
- Qwen/Qwen3.5-9B
---
Model Card for willhar/Qwen3.5-9B-AgentTuned-GGUF
This model is meant to improve upon base Qwen 3.5 9B's tool calling, instruction following, and logical thinking. It uses LORA weights merged into Qwen3.5 9B. 3200 training examples were seen during training, from the four datasets linked in the datasets tab.
Model Evaluation
Benchmarked using https://benchlocal.com/
Temperature = 0.5, default settings otherwise.
Initial Performance of Qwen3.5-9B
- BugFind-15 : 84
- InstructFollow-15 : 85
- ToolCall-15 : 80
Qwen3.5-9B-AgentTuned-GGUF
- BugFind-15 : 89
- InstructFollow-15 : 90
- ToolCall-15 : 93
Run willhar/Qwen3.5-9B-AgentTuned-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models