You can deploy this model and start earning money today!

RichardErkhov/
ihughes15234_-_phi_3_5_mini_20k_con4_bthrough_parmdiff-gguf

Name: ihughes15234_-_phi_3_5_mini_20k_con4_bthrough_parmdiff-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

phi_3_5_mini_20k_con4_bthrough_parmdiff - GGUF

Name	Quant method	Size
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q2_K.gguf	Q2_K	1.35GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.IQ3_XS.gguf	IQ3_XS	1.49GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.IQ3_S.gguf	IQ3_S	1.57GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q3_K_S.gguf	Q3_K_S	1.57GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.IQ3_M.gguf	IQ3_M	1.65GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q3_K.gguf	Q3_K	1.75GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q3_K_M.gguf	Q3_K_M	1.75GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q3_K_L.gguf	Q3_K_L	1.9GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.IQ4_XS.gguf	IQ4_XS	1.93GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q4_0.gguf	Q4_0	2.03GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.IQ4_NL.gguf	IQ4_NL	2.04GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q4_K_S.gguf	Q4_K_S	2.04GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q4_K.gguf	Q4_K	2.16GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q4_K_M.gguf	Q4_K_M	2.16GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q4_1.gguf	Q4_1	2.24GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q5_0.gguf	Q5_0	2.46GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q5_K_S.gguf	Q5_K_S	2.46GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q5_K.gguf	Q5_K	2.53GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q5_K_M.gguf	Q5_K_M	2.53GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q5_1.gguf	Q5_1	2.68GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q6_K.gguf	Q6_K	2.92GB
phi_3_5_mini_20k_con4_bthrough_parmdiff.Q8_0.gguf	Q8_0	3.78GB

Original model description:

base_model: unsloth/phi-3.5-mini-instruct-bnb-4bit language:

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