YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
pipe-agent-v6 (GGUF)
Screenpipe pipe agent v6 — fine-tuned Qwen3.5-9B with vision enabled.
What's new in v6
- Multimodal: can process screenshots/images alongside text (model_type: qwen3_5, not qwen3_5_text)
- Same tool-calling performance as v5 for text tasks
- Vision tower preserved from pretrained Qwen3.5-9B (frozen during LoRA training)
- Eval loss: 0.3210
Files
pipe-agent-v6-q4km.gguf— text model (Q4_K_M)pipe-agent-v6-mmproj-f16.gguf— vision projector (F16)Modelfile— ollama config
Usage with Ollama
ollama create pipe-agent:v6 -f Modelfile
ollama run pipe-agent:v6
- Downloads last month
- 458
Hardware compatibility
Log In to add your hardware
We're not able to determine the quantization variants.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support