Opt.Gear A family of large language models optimized for on-device inference, available in 1B, 270M and 1M parameter sizes Opt.Gear Technical Report Paper • 2608.01034 • Published 29 days ago • 1 OptGear/Opt.Gear-1B Text Generation • 0.8B • Updated 27 days ago • 64 OptGear/Opt.Gear-270M Text Generation • 0.2B • Updated 28 days ago • 81 OptGear/Opt.Gear-1M Text Generation • 1.04M • Updated 28 days ago • 57
Opt.Gear-QAT Quantization-aware large language models designed for efficient deployment on on-device platforms. OptGear/Opt.Gear-1B-qat-int4-per-channel-unquantized Text Generation • 0.8B • Updated 27 days ago • 33 OptGear/Opt.Gear-1B-qat-int4-g32-unquantized Text Generation • 0.8B • Updated 27 days ago • 31
OptGear/Opt.Gear-1B-qat-int4-per-channel-unquantized Text Generation • 0.8B • Updated 27 days ago • 33
Opt.Gear A family of large language models optimized for on-device inference, available in 1B, 270M and 1M parameter sizes Opt.Gear Technical Report Paper • 2608.01034 • Published 29 days ago • 1 OptGear/Opt.Gear-1B Text Generation • 0.8B • Updated 27 days ago • 64 OptGear/Opt.Gear-270M Text Generation • 0.2B • Updated 28 days ago • 81 OptGear/Opt.Gear-1M Text Generation • 1.04M • Updated 28 days ago • 57
Opt.Gear-QAT Quantization-aware large language models designed for efficient deployment on on-device platforms. OptGear/Opt.Gear-1B-qat-int4-per-channel-unquantized Text Generation • 0.8B • Updated 27 days ago • 33 OptGear/Opt.Gear-1B-qat-int4-g32-unquantized Text Generation • 0.8B • Updated 27 days ago • 31
OptGear/Opt.Gear-1B-qat-int4-per-channel-unquantized Text Generation • 0.8B • Updated 27 days ago • 33
