Opt.Gear Collection A family of large language models optimized for on-device inference, available in 1B, 270M and 1M parameter sizes • 4 items • Updated 21 days ago
Opt.Gear-QAT Collection Quantization-aware large language models designed for efficient deployment on on-device platforms. • 2 items • Updated Aug 2
Opt.Gear Collection A family of large language models optimized for on-device inference, available in 1B, 270M and 1M parameter sizes • 4 items • Updated 21 days ago