ConfidentialMind
/

Arcee-Blitz-GPTQ-G32-W4A16-MSE

Text Generation

confidentialmind

mistral-small-24b

4-bit precision

Model card Files Files and versions

🔥 Quantized Model: Arcee-Blitz_gptq_g32_4bit 🔥

The MSE based test did not work out too well; use non-MSE quant.

Downloads last month: 4

Safetensors

Model size

24B params

Tensor type

I32

·

BF16

·