Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,10 @@ license: llama3.3
|
|
| 4 |
|
| 5 |
SmartQuant v1 of Llama-3.3-70B-Instruct in just 2.39 bpw.
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
I'll do some qualification and perplexity runs next.
|
| 8 |
|
| 9 |
|
|
|
|
| 4 |
|
| 5 |
SmartQuant v1 of Llama-3.3-70B-Instruct in just 2.39 bpw.
|
| 6 |
|
| 7 |
+
With just 19.60GB it compares to those two:
|
| 8 |
+
* Llama-3.3-70B-Instruct-IQ2_XS.gguf IQ2_XS 21.14GB false Low quality, uses SOTA techniques to be usable.
|
| 9 |
+
* Llama-3.3-70B-Instruct-IQ2_XXS.gguf IQ2_XXS 19.10GB false Very low quality, uses SOTA techniques to be usable.
|
| 10 |
+
|
| 11 |
I'll do some qualification and perplexity runs next.
|
| 12 |
|
| 13 |
|