Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ This repository contains CPU-optimized GGUF quantizations of the Meta-Llama-3.1-
|
|
| 9 |
|
| 10 |
## Available Quantizations
|
| 11 |
|
| 12 |
-
1.
|
| 13 |
2. BF16: ~820 GB
|
| 14 |
3. Q8_0: ~410 GB
|
| 15 |
4. more coming...
|
|
@@ -100,4 +100,4 @@ The use of this model is subject to the [Llama 3.1 Community License](https://gi
|
|
| 100 |
|
| 101 |
Special thanks to the Meta AI team for creating and releasing the Llama 3.1 model series.
|
| 102 |
|
| 103 |
-
## Enjoy; more quants and perplexity benchmarks coming
|
|
|
|
| 9 |
|
| 10 |
## Available Quantizations
|
| 11 |
|
| 12 |
+
1. Q4_0_4_8 (CPU FMA-Optimized): ~246 GB
|
| 13 |
2. BF16: ~820 GB
|
| 14 |
3. Q8_0: ~410 GB
|
| 15 |
4. more coming...
|
|
|
|
| 100 |
|
| 101 |
Special thanks to the Meta AI team for creating and releasing the Llama 3.1 model series.
|
| 102 |
|
| 103 |
+
## Enjoy; more quants and perplexity benchmarks coming.
|