auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -23,8 +23,19 @@ more details, including on how to concatenate multi-part files.
|
|
| 23 |
|
| 24 |
| Link | Type | Size/GB | Notes |
|
| 25 |
|:-----|:-----|--------:|:------|
|
|
|
|
| 26 |
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q2_K.gguf) | i1-Q2_K | 26.4 | IQ3_XXS probably better |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.2 | optimal size/speed/quality |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
|
| 30 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
|
| 23 |
|
| 24 |
| Link | Type | Size/GB | Notes |
|
| 25 |
|:-----|:-----|--------:|:------|
|
| 26 |
+
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-IQ2_M.gguf) | i1-IQ2_M | 24.2 | |
|
| 27 |
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q2_K.gguf) | i1-Q2_K | 26.4 | IQ3_XXS probably better |
|
| 28 |
+
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.5 | fast, lower quality |
|
| 29 |
+
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-IQ3_XS.gguf) | i1-IQ3_XS | 29.1 | |
|
| 30 |
+
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-IQ3_S.gguf) | i1-IQ3_S | 30.9 | fast, beats Q3_K* |
|
| 31 |
+
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q3_K_S.gguf) | i1-Q3_K_S | 30.9 | IQ3_XS probably better |
|
| 32 |
+
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q3_K_M.gguf) | i1-Q3_K_M | 34.2 | IQ3_S probably better |
|
| 33 |
+
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q3_K_L.gguf) | i1-Q3_K_L | 37.1 | IQ3_M probably better |
|
| 34 |
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q4_K_S.gguf) | i1-Q4_K_S | 40.2 | optimal size/speed/quality |
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q4_K_M.gguf) | i1-Q4_K_M | 42.4 | fast, medium quality |
|
| 36 |
+
| [GGUF](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q5_K_S.gguf) | i1-Q5_K_S | 48.4 | |
|
| 37 |
+
| [PART 1](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 49.7 | |
|
| 38 |
+
| [PART 1](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/SpellBlade-i1-GGUF/resolve/main/SpellBlade.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 57.5 | practically like static Q6_K |
|
| 39 |
|
| 40 |
|
| 41 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|