Commit
•
702d501
1
Parent(s):
725ec6d
Add GGUF links
Browse files
README.md
CHANGED
|
@@ -127,7 +127,17 @@ You can try other similar prompts, we've had success with them, but this remains
|
|
| 127 |
---
|
| 128 |
## GGUF Quants
|
| 129 |
|
| 130 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
|
| 132 |
---
|
| 133 |
|
|
|
|
| 127 |
---
|
| 128 |
## GGUF Quants
|
| 129 |
|
| 130 |
+
[GGUF model card](https://huggingface.co/disinfozone/Disinfo4_mistral-ft-optimized-1218_GGUF)
|
| 131 |
+
|
| 132 |
+
Typically I like Q5_K_M or Q8_0. You get better quality running the highest quant you can, especially with these small models. I haven't bothered with quants smaller than Q4.
|
| 133 |
+
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|
| 134 |
+
| ---- | ---- | ---- | ---- | ---- | ----- |
|
| 135 |
+
| [Disinfo4_mistral-ft-optimized-1218.Q4_K_S.gguf](https://huggingface.co/disinfozone/Disinfo4_mistral-ft-optimized-1218_GGUF/blob/main/Disinfo4_mistral-ft-optimized-1218.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
|
| 136 |
+
| [Disinfo4_mistral-ft-optimized-1218.Q4_K_M.gguf](https://huggingface.co/disinfozone/Disinfo4_mistral-ft-optimized-1218_GGUF/blob/main/Disinfo4_mistral-ft-optimized-1218.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
|
| 137 |
+
| [Disinfo4_mistral-ft-optimized-1218.Q5_K_S.gguf](https://huggingface.co/disinfozone/Disinfo4_mistral-ft-optimized-1218_GGUF/blob/main/Disinfo4_mistral-ft-optimized-1218.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
|
| 138 |
+
| [disinfo4_mistral-ft-optimized-1218.Q5_K_M.gguf](https://huggingface.co/disinfozone/Disinfo4_mistral-ft-optimized-1218_GGUF/blob/main/disinfo4_mistral-ft-optimized-1218.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
|
| 139 |
+
| [Disinfo4_mistral-ft-optimized-1218.Q6_K.gguf](https://huggingface.co/disinfozone/Disinfo4_mistral-ft-optimized-1218_GGUF/blob/main/Disinfo4_mistral-ft-optimized-1218.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
|
| 140 |
+
| [disinfo4_mistral-ft-optimized-1218.gguf](https://huggingface.co/disinfozone/Disinfo4_mistral-ft-optimized-1218_GGUF/blob/main/disinfo4_mistral-ft-optimized-1218.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
|
| 141 |
|
| 142 |
---
|
| 143 |
|