You can deploy this model and start earning money today!

RichardErkhov/
MarcelPower_-_Phi-3.5-CodeAlpaca18k-FFT-gguf

Name: MarcelPower_-_Phi-3.5-CodeAlpaca18k-FFT-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Phi-3.5-CodeAlpaca18k-FFT - GGUF

Name	Quant method	Size
Phi-3.5-CodeAlpaca18k-FFT.Q2_K.gguf	Q2_K	1.35GB
Phi-3.5-CodeAlpaca18k-FFT.IQ3_XS.gguf	IQ3_XS	1.49GB
Phi-3.5-CodeAlpaca18k-FFT.IQ3_S.gguf	IQ3_S	1.57GB
Phi-3.5-CodeAlpaca18k-FFT.Q3_K_S.gguf	Q3_K_S	1.57GB
Phi-3.5-CodeAlpaca18k-FFT.IQ3_M.gguf	IQ3_M	1.65GB
Phi-3.5-CodeAlpaca18k-FFT.Q3_K.gguf	Q3_K	1.75GB
Phi-3.5-CodeAlpaca18k-FFT.Q3_K_M.gguf	Q3_K_M	1.75GB
Phi-3.5-CodeAlpaca18k-FFT.Q3_K_L.gguf	Q3_K_L	1.9GB
Phi-3.5-CodeAlpaca18k-FFT.IQ4_XS.gguf	IQ4_XS	1.93GB
Phi-3.5-CodeAlpaca18k-FFT.Q4_0.gguf	Q4_0	2.03GB
Phi-3.5-CodeAlpaca18k-FFT.IQ4_NL.gguf	IQ4_NL	2.04GB
Phi-3.5-CodeAlpaca18k-FFT.Q4_K_S.gguf	Q4_K_S	2.04GB
Phi-3.5-CodeAlpaca18k-FFT.Q4_K.gguf	Q4_K	2.16GB
Phi-3.5-CodeAlpaca18k-FFT.Q4_K_M.gguf	Q4_K_M	2.16GB
Phi-3.5-CodeAlpaca18k-FFT.Q4_1.gguf	Q4_1	2.24GB
Phi-3.5-CodeAlpaca18k-FFT.Q5_0.gguf	Q5_0	2.46GB
Phi-3.5-CodeAlpaca18k-FFT.Q5_K_S.gguf	Q5_K_S	2.46GB
Phi-3.5-CodeAlpaca18k-FFT.Q5_K.gguf	Q5_K	2.53GB
Phi-3.5-CodeAlpaca18k-FFT.Q5_K_M.gguf	Q5_K_M	2.53GB
Phi-3.5-CodeAlpaca18k-FFT.Q5_1.gguf	Q5_1	2.68GB
Phi-3.5-CodeAlpaca18k-FFT.Q6_K.gguf	Q6_K	2.92GB
Phi-3.5-CodeAlpaca18k-FFT.Q8_0.gguf	Q8_0	3.78GB

Original model description:

base_model: unsloth/Phi-3.5-mini-instruct language:

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.