Engineering ready
Qwen3.8 27B FP8 Production Package
Qwen / Qwen3.8 27B · FP8 · Engineering status: Engineering ready
Transformation lineage
Base releaseQwen3.8 27B
Model engineeringFP8 Quantization, Runtime packaging, Evaluation and benchmarking
Delivery optionsDownload package / Host with FusionPointAI / Download + host
Transparent pricing
- Base model engineeringUSD 17,400.00
- FP8 QuantizationUSD 5,900.00
- Runtime packagingUSD 2,800.00
- Evaluation and benchmarkingUSD 3,600.00
- Download packageUSD 1,500.00
- Managed deployment setupUSD 3,200.00
- One-time engineeringUSD 34,400.00
Monthly hosting
- 1 x nvidia-l40sUSD 506.00
- Monthly hostingUSD 506.00
Quantization
SourceSource
TransformationEstimated until measured during engineering
GPU topology
1 × nvidia-l40s
transformers
Download or managed hosting
Artifact, config, tokenizer, checksums
GPU allocation, runtime, endpoint and monitoring