This model was quantized using oQ (oMLX v0.7.0.dev2) mixed-precision quantization.
Independent publisher
Johannes Uusikuu
Johneeee
Small omlx models without vision & mtp for m1 m2 or low memory macs
Models in Library3
Datasets in Library0
Models on Hugging Face45
Followers1
Models
This model was quantized using oQ (oMLX v0.7.0.dev2) mixed-precision quantization.
This model was quantized using oQ (oMLX v0.7.0.dev2) mixed-precision quantization.