Models
| tenant | namespace | model name | gpu count | vram (GB) | cpu | memory (GB) | standby | state | snapshot nodes | revision | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| gpu | pageable | pinned | ||||||||||
| public | TinyLlama | TinyLlama-1.1B-Chat-v1.0 | 1 | 6.0 | 20.0 | 18.0 | Blob | Blob | Blob | Normal | ['node3'] | 100 |
| public | TinyLlama | TinyLlama-1.1B-Chat-v1.0_13GB | 1 | 13.8 | 20.0 | 18.0 | Blob | Blob | Blob | Normal | ['node3'] | 106 |
| public | TinyLlama | TinyLlama-1.1B-Chat-v1.0_2gpu | 2 | 13.8 | 20.0 | 50.0 | Blob | Mem | Blob | Normal | ['node3'] | 109 |
Summary
Model Count |
3 |
GPU Count |
4 |
VRAM (GB) |
47.4 GB |
CPU Cores |
60.0 |
Memory (GB) |
86.0 GB |