Static quantization of MN-12B-Mag-Mell-R1
| File | Notes |
|---|---|
| Q6_K with select tensors quantized to Q8_0 7.26 bpw Quantized from BF16 Very close in fidelity to full precision |
- Downloads last month
- 9
Hardware compatibility
Log In to add your hardware
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Valeciela/MN-12B-Mag-Mell-R1-Q6_K_XL-GGUF
Base model
inflatebot/MN-12B-Mag-Mell-R1