README table: gpu-vision slots/ctx aligned to roster (parallel 1, 131K)
This commit is contained in:
@@ -63,7 +63,7 @@ When all GPUs are saturated, requests enter a polling queue (500ms intervals) in
|
||||
|-----|-------|------|-------|
|
||||
| Strix Halo | qwen3.6-35B-A3B (MoE) | 65GB | 2 | 262K | General quality |
|
||||
| RTX 3090 | gpu-dense (Qwen3.8-27B-Uncensored) | 24GB | 1 | 131K | Dense, general |
|
||||
| RTX 5070 | gpu-vision (VLM) | 12GB | 2 | 262K | Speed, vision |
|
||||
| RTX 5070 | gpu-vision (VLM) | 12GB | 1 | 131K | Speed, vision |
|
||||
|
||||
## Maintenance
|
||||
|
||||
|
||||
Reference in New Issue
Block a user