ChipsHacker Noonabout 5 hours ago
GLM-4.7-Flash on 2x RTX 3090: My Hands-On Experience
9 min read
GLM-4.7-Flash hits 88.5 tokens per second at 4K context on a single RTX 3090 but drops to 16.8 at 128K. The model beats Qwen3.5:27b at short context but loses at long context. Two RTX 3090s in tensor parallel reach 498 tokens per second batched.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyNvidia
Summary by ByteBrief
