Hugging Face's logo

JeiganS
/
ML2-123B-Magnum-Diamond_fp8

Text Generation
Safetensors
English
mistral
vllm
conversational
modelopt
Model card Files
xet
Community

FP8 quantization using TensorRT-LLM

Downloads last month
29
Safetensors
Model size
123B params
Tensor type
BF16
·
F8_E4M3
·
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for JeiganS/ML2-123B-Magnum-Diamond_fp8

Base model

mistralai/Mistral-Large-Instruct-2411
Finetuned
Doctor-Shotgun/ML2-123B-Magnum-Diamond
Quantized
(7)
this model