Downloads · 30 days
108
31% of all-time downloads
Qwen3.5-9B-FineTuned
qwertt2005/Qwen3.5-9B-FineTuned
Qwen3.5-9B-FineTuned is a text generation model from qwertt2005. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Fine-tuned version of Qwen3.5-9B trained on NVIDIA H100 80GB across 159,082 curated samples blending reasoning, conversational alignment, and domain knowledge.
All-time downloads
343
Public
Repo size
35.1 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf34.9 GB · 99%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Access
- Public
- Created
- Aug 23, 2026
- Updated
- Aug 23, 2026
- SHA
- 143e8f84
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.5-9B Fine-Tuned (GGUF & LoRA)
Fine-tuned version of Qwen3.5-9B trained on NVIDIA H100 80GB across 159,082 curated samples blending reasoning, conversational alignment, and domain knowledge.
📊 Training Mixture (159,082 samples)
- HuggingFaceTB/smoltalk (50,000 samples) - Conversational & Alignment SFT
- open-r1/OpenR1-Math-220k (49,999 samples) - Step-by-step mathematical reasoning (<think> traces)
- HuggingFaceFW/fineweb (19,995 samples) - High-quality web corpus
- OpenAssistant/oasst2 (14,088 samples) - Human-rated RLHF multi-turn data
- teknium/OpenHermes-2.5 (25,000 samples) - GPT-4 quality instruction following
🚀 Quick Start with Ollama
Run directly on your local machine:
📦 Files Included
- (5.4 GB) - Fast 4-bit Medium quantization
- (9.2 GB) - High precision 8-bit quantization
- (18.0 GB) - Full 16-bit precision GGUF
-
- PEFT LoRA adapter files
- Task
- Text Generation
- License
- apache-2.0
- Created
- Aug 23, 2026
- Updated
- Aug 23, 2026