Quantized 4bit MLX version of https://huggingface.co/prithivMLmods/Viper-Coder-v1.7-Vsm6
- Downloads last month
- 13
Model size
15B params
Tensor type
U32
·
F16 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Lowkey-Loki/Viper-Coder-v1.7-Vsm6-MLX-4bit
Base model
prithivMLmods/Jolt-v0.1 Finetuned
prithivMLmods/Viper-Coder-v0.1 Finetuned
prithivMLmods/Viper-Coder-v1.1 Finetuned
prithivMLmods/Viper-Coder-Hybrid-v1.3 Finetuned
prithivMLmods/Viper-Coder-v1.6-r999 Finetuned
prithivMLmods/Viper-Coder-v1.7-Vsm6