zaharinea
@zaharinea
Joined July 2025
Projects
Public
Gemma 4 26B A4B optimized with Quantization-Aware Training (QAT)
MODEL
2
@zaharinea
Joined July 2025
Projects
Gemma 4 26B A4B optimized with Quantization-Aware Training (QAT)
MODEL
2
@zaharinea
Joined July 2025
Projects
Gemma 4 26B A4B optimized with Quantization-Aware Training (QAT)
MODEL
2
31B dense Gemma4 variant. Supports vision input, reasoning, and tool calls.
MODEL
3
Dense 27B Qwen 3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.
MODEL
3
Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.
MODEL
8
Gemma 4 is the latest on-device model family from Google. This is the 26B (active 4B) MoE version. Supports vision and reasoning.
MODEL
6
31B dense Gemma4 variant. Supports vision input, reasoning, and tool calls.
MODEL
3
Dense 27B Qwen 3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.
MODEL
3
Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.
MODEL
8
Gemma 4 is the latest on-device model family from Google. This is the 26B (active 4B) MoE version. Supports vision and reasoning.
MODEL
6