Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ Based on Smollm2 by HuggingfaceTB, Tinyparm v2 (this version) has very strong pe
|
|
| 22 |
# Which quant is right for you?
|
| 23 |
|
| 24 |
- ***F16:*** Highest quality answers, Not needed for most use cases due to its heavier size.
|
| 25 |
-
- ***Q8:*** Very high-quality answers, highly recommended! easy to run on modern mobile devices such as phones (
|
| 26 |
- ***Q5:*** High quality answers, recommended but Q4 is very similar.
|
| 27 |
- ***Q4:*** Good quality answers, highly recommended! very easy to run on most devices due to its smaller size, although quality is lower. can be run on ~1 - 2GB vram
|
| 28 |
|
|
|
|
| 22 |
# Which quant is right for you?
|
| 23 |
|
| 24 |
- ***F16:*** Highest quality answers, Not needed for most use cases due to its heavier size.
|
| 25 |
+
- ***Q8:*** Very high-quality answers, highly recommended! easy to run on modern mobile devices such as phones (test on Z fold 5 via llama.cpp: 14.03 t/s for token generation.)
|
| 26 |
- ***Q5:*** High quality answers, recommended but Q4 is very similar.
|
| 27 |
- ***Q4:*** Good quality answers, highly recommended! very easy to run on most devices due to its smaller size, although quality is lower. can be run on ~1 - 2GB vram
|
| 28 |
|