Gemma 4
on 2× NVIDIA RTX 2000 Ada · TensorSharp
Summary
User benchmarks TensorSharp multi-GPU tensor parallelism on 2x RTX 2000 Ada 16GB.
Gemma 4 E4B Q8_0 is the primary model among several tested.
TP=2 raises decode speed from 37.3 to 51.7 tok/s.
on 2× NVIDIA RTX 2000 Ada · TensorSharp