granite3-moe:1b-instruct-q4_0

83.5K 9 months ago

The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.

tools 1b 3b
... /
params
5d4667f097b4 · 15B
{
"num_gpu": 23
}