Update README.md
Browse files
README.md
CHANGED
|
@@ -9,8 +9,8 @@ tags:
|
|
| 9 |
|
| 10 |
27 TPS with Draft model: [DeepScaleR-1.5B-Preview-Q8](https://huggingface.co/mlx-community/DeepScaleR-1.5B-Preview-Q8)
|
| 11 |
|
| 12 |
-
oh yeah
|
| 13 |
-
|
| 14 |
|
| 15 |
|
| 16 |
Macbook M4 Max: high power (10 TPS on low-power, GPU draws only 5 watts...less than your brain)
|
|
@@ -20,7 +20,7 @@ system prompt: "You are Fuse01. You answer very direct brief and concise"
|
|
| 20 |
prompt: "Write a quick sort in C++"
|
| 21 |
|
| 22 |
Context: 131072, Temp: 0
|
| 23 |
-
|
| 24 |
|
| 25 |
|
| 26 |
Try this model in Visual Studio Code with the Roo Code extension. Starting in Architect Mode and letting it auto switch to Code Mode.... it actually spits decent code for small projects with multiple files.
|
|
|
|
| 9 |
|
| 10 |
27 TPS with Draft model: [DeepScaleR-1.5B-Preview-Q8](https://huggingface.co/mlx-community/DeepScaleR-1.5B-Preview-Q8)
|
| 11 |
|
| 12 |
+
oh yeah! 100% faster for math/code stuff.
|
| 13 |
+
.
|
| 14 |
|
| 15 |
|
| 16 |
Macbook M4 Max: high power (10 TPS on low-power, GPU draws only 5 watts...less than your brain)
|
|
|
|
| 20 |
prompt: "Write a quick sort in C++"
|
| 21 |
|
| 22 |
Context: 131072, Temp: 0
|
| 23 |
+
.
|
| 24 |
|
| 25 |
|
| 26 |
Try this model in Visual Studio Code with the Roo Code extension. Starting in Architect Mode and letting it auto switch to Code Mode.... it actually spits decent code for small projects with multiple files.
|