Opt.Gear A family of large language models optimized for on-device inference, available in 1B, 270M and 1M parameter sizes OptGear/Opt.Gear-1B Text Generation • 0.8B • Updated 8 days ago • 39 OptGear/Opt.Gear-270M Text Generation • 0.2B • Updated 9 days ago • 32 OptGear/Opt.Gear-1M Text Generation • 1.04M • Updated 9 days ago • 33
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 8 days ago • 19 OptGear/Opt.Gear-1B-qat-int4-g32-unquantized Text Generation • 0.8B • Updated 8 days ago • 22
OptGear/Opt.Gear-1B-qat-int4-per-channel-unquantized Text Generation • 0.8B • Updated 8 days ago • 19
Opt.Gear A family of large language models optimized for on-device inference, available in 1B, 270M and 1M parameter sizes OptGear/Opt.Gear-1B Text Generation • 0.8B • Updated 8 days ago • 39 OptGear/Opt.Gear-270M Text Generation • 0.2B • Updated 9 days ago • 32 OptGear/Opt.Gear-1M Text Generation • 1.04M • Updated 9 days ago • 33
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 8 days ago • 19 OptGear/Opt.Gear-1B-qat-int4-g32-unquantized Text Generation • 0.8B • Updated 8 days ago • 22
OptGear/Opt.Gear-1B-qat-int4-per-channel-unquantized Text Generation • 0.8B • Updated 8 days ago • 19
