Static quantization of Cydonia-v4.1-MS3.2-Magnum-Diamond-24B

Quantized Fox Girl

File Notes

Cydonia-v4.1-MS3.2-Magnum-Diamond-24B.Q6_K_XL.gguf

Q6_K with select tensors quantized to Q8_0
7.10 bpw
Quantized from BF16
Very close in fidelity to full precision

Mistral-Small-3.1-24B-Instruct-2503-mmproj-bf16.gguf

Multimodal Projector
BF16
Native precision
Downloads last month
30
GGUF
Model size
24B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

6-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Valeciela/Cydonia-v4.1-MS3.2-Magnum-Diamond-24B-Q6_K_XL-GGUF

Quantized
(8)
this model