AnalysisAI Models
6 hours ago
User runs MiniMax 2.7 locally with high throughput
Achieves 47 tokens/s and 1200 tokens processing on 96GB VRAM and 192GB DDR5. Model described as excellent for instruction following and tool calling.
·
6 hours ago
Achieves 47 tokens/s and 1200 tokens processing on 96GB VRAM and 192GB DDR5. Model described as excellent for instruction following and tool calling.