auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -48,7 +48,25 @@ more details, including on how to concatenate multi-part files.
|
|
| 48 |
|
| 49 |
| Link | Type | Size/GB | Notes |
|
| 50 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 54 |
types (lower is better):
|
|
|
|
| 48 |
|
| 49 |
| Link | Type | Size/GB | Notes |
|
| 50 |
|:-----|:-----|--------:|:------|
|
| 51 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate |
|
| 52 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.2 | mostly desperate |
|
| 53 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | |
|
| 54 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | |
|
| 55 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.8 | |
|
| 56 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality |
|
| 57 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | |
|
| 58 |
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better |
|
| 59 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.1 | lower quality |
|
| 60 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better |
|
| 61 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | |
|
| 62 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better |
|
| 63 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better |
|
| 64 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | |
|
| 65 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS |
|
| 66 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.5 | optimal size/speed/quality |
|
| 67 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.7 | fast, recommended |
|
| 68 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | |
|
| 69 |
+
| [GGUF](https://huggingface.co/mradermacher/Viking-SlimInstruct-V1-7B-i1-GGUF/resolve/main/Viking-SlimInstruct-V1-7B.i1-Q6_K.gguf) | i1-Q6_K | 6.3 | practically like static Q6_K |
|
| 70 |
|
| 71 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 72 |
types (lower is better):
|