Design validated
Production distillation package for GPT-OSS 120B
GPT-OSS / GPT-OSS 120B · Distillation · Engineering status: Design validated
Transformation lineage
Base releaseGPT-OSS 120B
Model engineeringDistillation, Evaluation and benchmarking
Delivery optionsDownload package / Host with FusionPointAI / Download + host
Package profile: Throughput-optimized distillation. The student architecture is selected and benchmarked during engineering; no prebuilt student checkpoint is implied.
Transparent pricing
- Base model engineeringUSD 59,160
- DistillationUSD 86,275
- Evaluation and benchmarkingUSD 3,600
- Download packageUSD 1,500
- One-time engineeringUSD 150,535
Quantization
SourceSource
TransformationEstimated until measured during engineering
GPU topology
Validated × GPU targeting
transformers
Download or managed hosting
Artifact, config, tokenizer, checksums
GPU allocation, runtime, endpoint and monitoring