Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
Llama 3.1 405B Quants
|
| 5 |
- IQ1_S: 86.8 GB
|
| 6 |
- IQ1_M: 95.1 GB
|
|
|
|
| 7 |
|
| 8 |
Quantization from BF16 here:
|
| 9 |
https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/
|
|
|
|
| 4 |
Llama 3.1 405B Quants
|
| 5 |
- IQ1_S: 86.8 GB
|
| 6 |
- IQ1_M: 95.1 GB
|
| 7 |
+
- IQ2_XXS: 109.0 GB
|
| 8 |
|
| 9 |
Quantization from BF16 here:
|
| 10 |
https://huggingface.co/nisten/meta-405b-instruct-cpu-optimized-gguf/
|