Gemma 4 26B
on NVIDIA RTX 4060 Laptop 8GB · llama.cpp
Oct 14, 2026
Summary
User reports Gemma 4 26B MoE at 60+ tok/s on an RTX 4060 Laptop, up from 40 tok/s with standard llama.cpp.
Setup is llama.cpp with MTP speculative decoding plus a custom DeepSeek-inspired hot-expert caching scheme that keeps frequently used experts on the GPU.
The user asks for further performance ideas without changing the model.