llamaperf
Submit

Gemma 4 26B (4B active)

on NVIDIA RTX 4090 · Ollama

Tone: positiveNVIDIA hardware
May 1, 2026
Share
Throughput
149.6 t/s gen
Quant
Q4_K_M (GGUF)

Use cases

text-generation

Summary

User reports about 150 t/s generation. The model is described as a star performer.