dicksondickson/Carbon-X-oQ4e-bf16-MLX
This model is a quantization of:
https://huggingface.co/HuggingFaceBio/Carbon-X
This model was quantized using oQ (oMLX 0.7.3.dev2) imatrix, mixed-precision quantization with Better Low-Bit oQ.
Important tensors are left at bf16 which is for Apple M3 chips and later.
Run the model using oMLX:
https://github.com/jundot/omlx
The tokenizer has been patch to run with oMLX and runs completely offline.
Please use the following settings in oMLX:
Model Settings → Advanced → Trust Remote Code → on
| Temperature | 0.6
| Top-p | 0.95
| Top-k | 20
| Thinking | Off (enable_thinking=False)
| Max tokens | Cap to what you need (e.g. 1024–4096) | Long DNA generation is slow, and its quality drops the longer it runs
| Context | Up to 40,960 tokens (~245 kbp of DNA)
- Downloads last month
- 43
Model size
15B params
Tensor type
U32
·
BF16 ·
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