Celeste Imperia | Phi-3.5-mini-instruct (Optimized GGUF)
Highly-optimized GGUF weights for Microsoft's Phi-3.5-mini, specifically forged for high-reasoning tasks on edge hardware.
🛠️ The Forge
- Rig: i5-11400 / RTX A4000 / 40GB RAM
- Context: Validated for 128k long-context execution.
📂 Available Precisions
- FP16 Master: The full-fidelity reference file.
- Q8_0 Professional: Recommended for complex coding and math.
- Q4_K_M Mobile: Balanced performance for local agentic workflows.
- Downloads last month
- 16
Hardware compatibility
Log In to add your hardware
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support