lm-studio load error
#1
by
gptwin
- opened
lms load nvidia-nemotron-nano-9b-v2s
Loading model "mlx-community/NVIDIA-Nemotron-Nano-9B-v2-4bits"...
Error: Failed to load model ] 36.49%
(X) CAUSE
Error when loading model: ValueError: Model type nemotron_h not supported.
lms - LM Studio CLI - v0.0.47
- mxfp4 quantization support for gpt-oss
MLX version info:
- mlx-engine==2519a8b
- mlx==0.29.0
- mlx-lm==0.27.0
- mlx-vlm==0.3.3
this is not yet merged into the next version of MLX-LM you'd have to wait a little.