phi-2-GGUF

GGUF conversions of microsoft/phi-2.

These weights were converted with llama.cpp and quantized for local / Ollama use. This is not the original model; it is a community conversion of the source weights.

Quantizations

Q4_K_M, Q5_K_M, Q8_0

Source

Base model: microsoft/phi-2
Converted by HF-2-GGUF

Downloads last month: 57

GGUF

Model size

3B params

Architecture

phi2

Hardware compatibility

4-bit

5-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mparvin/phi-2-GGUF

Base model

microsoft/phi-2

Quantized

(63)

this model