Update README.md
Browse files
README.md
CHANGED
|
@@ -16,4 +16,6 @@ Contains Q4 & Q8 quantized GGUFs for [google/gemma](https://huggingface.co/colle
|
|
| 16 |
| Variant | Device | Perf |
|
| 17 |
| - | - | - |
|
| 18 |
| Q4 | RTX 2070S | 22 tok/s |
|
| 19 |
-
|
|
|
|
|
|
|
|
|
|
| 16 |
| Variant | Device | Perf |
|
| 17 |
| - | - | - |
|
| 18 |
| Q4 | RTX 2070S | 22 tok/s |
|
| 19 |
+
| | M1 Pro 10-core GPU | 28 tok/s |
|
| 20 |
+
| Q8 | RTX 2070S | 7 tok/s (could only offload 23/29 layers to GPU) |
|
| 21 |
+
| | M1 Pro 10-core GPU | 17 tok/s |
|