large multi-GPU / rack-scale
[1] [14] [17]- Exact released checkpoint tensor payload510.29 GB storage · native mixed released precision[8]
N-gram memory placement: Host RAM offload with asynchronous prefetch is supported; GPU residency depends on the serving engine and configuration.
[4]- Engram native storage
- 202.76 GB[8]
- Remaining native storage
- 307.53 GB[8]
An independent NVMe implementation also exists; its reported performance has not been reproduced by us.
[12] [13]The released Engram tables occupy about 203GB including scales. Other checkpoint tensors occupy about 308GB, before KV cache and runtime overhead. These are storage footprints, not minimum VRAM requirements.
[8] [4]