Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- mistralai/Mistral-Small-24B-Instruct-2501
|
| 5 |
+
---
|
| 6 |
+
# Mistral-Small-24B-Instruct-2501-GGUF
|
| 7 |
+
|
| 8 |
+
This repo provides two GGUF quantizations of [mistralai/Mistral-Small-24B-Instruct-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501):
|
| 9 |
+
|
| 10 |
+
| Filename | File size | Description | TLDR |
|
| 11 |
+
| ------------------------------------------------ | --------- | ------------------------------------------------------------------------ | ---------------------------------------- |
|
| 12 |
+
| Mistral-Small-24B-Instruct-2501-q8_0-q4_K_S.gguf | 14.05GB | q4\_K\_S quantization using q8_0 for token embeddings and output tensors | Good quality, smaller size |
|
| 13 |
+
| Mistral-Small-24B-Instruct-2501-q8_0-q6_K.gguf | 19.67GB | q6_K quantization using q8_0 for token embeddings and output tensors | Practically perfect quality, larger size |
|