Engineering ready
GLM-4.6V FP8 Production Package
GLM / GLM-4.6V · FP8 · Engineering status: Engineering ready
Transformation lineage
Base releaseGLM-4.6V
Model engineeringquantization fp8, runtime optimization
Delivery optionsDownload package / Host with FusionPointAI / Download + host
Transparent pricing
- Base model engineeringUSD 59,160.00
- 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 76,160.00
Monthly hosting
- 2 x nvidia-h200-sxm-141gbUSD 4,690.00
- Monthly hostingUSD 4,690.00
Quantization
SourceSource
TransformationEstimated until measured during engineering
GPU topology
2 × nvidia-h200-sxm-141gb
transformers
Download or managed hosting
Artifact, config, tokenizer, checksums
GPU allocation, runtime, endpoint and monitoring