Update README.md
Browse files
README.md
CHANGED
|
@@ -270,12 +270,14 @@ It can be changed, e.g. `--temp 0.8`.
|
|
| 270 |
|
| 271 |
## Benchmarks
|
| 272 |
|
| 273 |
-
|
|
| 274 |
-
|
|
| 275 |
-
|
|
| 276 |
-
|
|
| 277 |
-
| AMD Ryzen Threadripper PRO 7995WX (znver4) |
|
| 278 |
-
| AMD Ryzen Threadripper PRO 7995WX (znver4) |
|
|
|
|
|
|
|
| 279 |
|
| 280 |
## About Quantization
|
| 281 |
|
|
|
|
| 270 |
|
| 271 |
## Benchmarks
|
| 272 |
|
| 273 |
+
| hardware | model\_filename | size | test | t/s |
|
| 274 |
+
| :----------------------------------------- | :--------------------------------------- | ---------: | ------------: | --------------: |
|
| 275 |
+
| Apple M2 Ultra (Metal GPU) | granite-34b-code-instruct.Q5\_0 | 22.03 GiB | pp512 | 186.14 |
|
| 276 |
+
| Apple M2 Ultra (Metal GPU) | granite-34b-code-instruct.Q5\_0 | 22.03 GiB | tg16 | 14.13 |
|
| 277 |
+
| AMD Ryzen Threadripper PRO 7995WX (znver4) | granite-34b-code-instruct.Q8\_0 | 33.82 GiB | pp512 | 94.34 |
|
| 278 |
+
| AMD Ryzen Threadripper PRO 7995WX (znver4) | granite-34b-code-instruct.Q8\_0 | 33.82 GiB | tg16 | 5.61 |
|
| 279 |
+
| AMD Ryzen Threadripper PRO 7995WX (znver4) | granite-34b-code-instruct.Q5\_0 | 22.03 GiB | pp512 | 95.08 |
|
| 280 |
+
| AMD Ryzen Threadripper PRO 7995WX (znver4) | granite-34b-code-instruct.Q5\_0 | 22.03 GiB | tg16 | 7.78 |
|
| 281 |
|
| 282 |
## About Quantization
|
| 283 |
|