Commit
•
ad58b2e
1
Parent(s):
ff0b8c0
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -40,7 +40,10 @@ more details, including on how to concatenate multi-part files.
|
|
| 40 |
| Link | Type | Size/GB | Notes |
|
| 41 |
|:-----|:-----|--------:|:------|
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/Aura-8B-i1-GGUF/resolve/main/Aura-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
|
|
|
|
| 43 |
| [GGUF](https://huggingface.co/mradermacher/Aura-8B-i1-GGUF/resolve/main/Aura-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
|
|
|
|
|
|
|
| 44 |
|
| 45 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 46 |
types (lower is better):
|
|
|
|
| 40 |
| Link | Type | Size/GB | Notes |
|
| 41 |
|:-----|:-----|--------:|:------|
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/Aura-8B-i1-GGUF/resolve/main/Aura-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/Aura-8B-i1-GGUF/resolve/main/Aura-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
|
| 44 |
| [GGUF](https://huggingface.co/mradermacher/Aura-8B-i1-GGUF/resolve/main/Aura-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/Aura-8B-i1-GGUF/resolve/main/Aura-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/Aura-8B-i1-GGUF/resolve/main/Aura-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
|
| 47 |
|
| 48 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 49 |
types (lower is better):
|