PathOS — Distilled GGUF for Ollama
AI pathologist that runs offline on any laptop via Ollama.
You can use this model locally on your computer through Ollama - https://ollama.com/dhairyapandya/pathos
Quick Start
# 1. Download pathos-Q8_0.gguf and Modelfile from this repo
# 2. Place both files in the same folder, then:
ollama create pathos -f Modelfile
ollama run pathos "Is malignancy present?"
Model Details
| Property | Value |
|---|---|
| Base model | Gemma 4 E2B (2.6B params) |
| Training | SFT + GRPO distillation |
| Quantization | Q8_0 |
| Source | dhairyapandya/pathos-gemma4-distilled-rl-histopathology |
Distilled Techniques
All 6 inference-time techniques baked into the weights:
- Constrained decoding — always produces
<answer>tags - Anti-hedging — never says "cannot determine"
- Static RAG — few-shot exemplars in system prompt
- CoT routing — adapts reasoning to question type
- Per-type templates — YN/tissue/open formats
- Format compliance — GRPO reward shaping
- Downloads last month
- 6
GGUF
Model size
5B params
Architecture
gemma4
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support