README table: gpu-vision slots/ctx aligned to roster (parallel 1, 131K)

This commit is contained in:
2026-09-20 15:33:31 +00:00
parent 4c6cf66aed
commit 82464d2158
+1 -1
View File
@@ -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 | | 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 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 ## Maintenance