Models
tenant | namespace | model name | gpu count | vram (GB) | cpu | memory (GB) | standby | state | snapshot nodes | revision | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|
gpu | pageable | pinned | ||||||||||
public | THUDM | chatglm3-6b | 1 | 13.8 | 12.0 | 20.0 | Blob | Blob | Blob | Normal | ['node2'] | 160 |
public | THUDM | chatglm3-6b-128k | 1 | 13.8 | 12.0 | 20.0 | Blob | Blob | Blob | Normal | ['node2'] | 164 |
public | THUDM | chatglm3-6b-32k | 1 | 13.8 | 12.0 | 20.0 | Blob | Blob | Blob | Normal | ['node2'] | 162 |
Summary
Model Count |
3 |
Required GPU Count |
3 |
Required VRAM (GB) |
41.4 GB |
Required CPU Cores |
36.0 |
Required Memory (GB) |
60.0 GB |