ssfdre38/ gemma4-turbo:26b

16.3K 24 minutes ago

Gemma 4 Turbo is an optimized version of Google's Gemma 4 (9B) model, achieving 51% faster CPU inference through int4 quantization and performance tuning. Ideal for local AI assistants, tool calling, and chat applications on Windows systems without GPU.

vision tools thinking audio e2b e4b 26b 31b
... /
system
d25021efc88f · 342B
Gemma 4 Turbo 26b is the high-performance edition of the Gemma 4 Turbo family — optimized for complex reasoning, coding, and multi-step tasks on CPU. Turboquant inference tuning with KV cache quantization (Stage 1 TurboQuant) delivers maximum throughput on 16GB+ RAM systems. Ideal for demanding local AI workloads without GPU acceleration.