Hindsight Model Selects
Collection
Local models for running Hindsight memory for agents. • 9 items • Updated • 1
dicksondickson/Qwen3.5-4B-oQ8e-mtp-bf16-MLX
This model is a quantization of:
https://huggingface.co/Qwen/Qwen3.5-4B
This checkpoint was quantized using oMLX 0.7.0 with imatrix enabled.
Important tensors are left at bf16 which is for Apple M3 chips and later.
Run the model using oMLX:
https://github.com/jundot/omlx
- Downloads last month
- 72
Model size
5B params
Tensor type
U32
·
BF16 ·
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support