latest
5.5GB
It uses this one Q4_K_M-imat (4.89 BPW) quant for up to 12288 context sizes. for less than 8gb vram
Vision
8B
780 Pulls Updated 4 months ago
56bb8bd477a5 · 96B
{
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>"
]
}