CloudXDAabout 4 hours ago
Local LLM test on RTX 4070 Ti picks one winner
1 min read
A user tested DeepSeek-R1 8B, Qwen 3.5 9B, and Gemma 4 E4B on an RTX 4070 Ti with 12GB VRAM for real workflow tasks. DeepSeek-R1 loaded quickly but spent 24 seconds thinking before outputting. Only one model earned a permanent spot on the machine.
Level
Hype check
Tap to vote and see what everyone thinks.
