GPT-OSS / GPT-OSS 20B
GPT-OSS 20B MXFP4 quantization
Estimado ate medicao durante a engenharia
Before → After
Lancamento baseCheckpoint verificado
21.000B
21.000B
quantizationMXFP4
Quality retention target
Quality retention target
Artefacto de producaoArtefacto
Relatorio de linhagem e benchmark
Relatorio de linhagem e benchmark
Destino de GPU
Pesos e cache KVEstimado ate medicao durante a engenharia
Estimated VRAMMeasured and certified results are delivered with the project.
Empacotamento de runtimetransformers
Preco transparente
Nao disponivel para encomenda