iAkashPaul
/

gemma-7b-it-gguf

Inference Endpoints

Model card Files Files and versions Community

iAkashPaul commited on Feb 21

Commit

7e1dc6e

•

1 Parent(s): 9539c6d

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -17,5 +17,5 @@ Contains Q4 & Q8 quantized GGUFs for [google/gemma](https://huggingface.co/colle
 | Variant | Device | Perf |
 | - | - | - |
-| Q4 | RTX 2070S | 22tok/s |
-| Q8 | RTX 2070S | 7tok/s(could only offload 23/29 layers to GPU) |

 | Variant | Device | Perf |
 | - | - | - |
+| Q4 | RTX 2070S | 22 tok/s |
+| Q8 | RTX 2070S | 7 tok/s (could only offload 23/29 layers to GPU) |