auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -33,7 +33,16 @@ more details, including on how to concatenate multi-part files.
|
|
| 33 |
| Link | Type | Size/GB | Notes |
|
| 34 |
|:-----|:-----|--------:|:------|
|
| 35 |
| [GGUF](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q2_K.gguf) | Q2_K | 45.3 | |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
| [PART 1](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q4_K_S.gguf.part2of2) | Q4_K_S | 69.7 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 39 |
types (lower is better):
|
|
|
|
| 33 |
| Link | Type | Size/GB | Notes |
|
| 34 |
|:-----|:-----|--------:|:------|
|
| 35 |
| [GGUF](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q2_K.gguf) | Q2_K | 45.3 | |
|
| 36 |
+
| [PART 1](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q3_K_S.gguf.part2of2) | Q3_K_S | 52.9 | |
|
| 37 |
+
| [PART 1](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q3_K_M.gguf.part2of2) | Q3_K_M | 59.2 | lower quality |
|
| 38 |
+
| [PART 1](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q3_K_L.gguf.part2of2) | Q3_K_L | 64.7 | |
|
| 39 |
+
| [PART 1](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.IQ4_XS.gguf.part2of2) | IQ4_XS | 66.1 | |
|
| 40 |
| [PART 1](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q4_K_S.gguf.part2of2) | Q4_K_S | 69.7 | fast, recommended |
|
| 41 |
+
| [PART 1](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q4_K_M.gguf.part2of2) | Q4_K_M | 73.3 | fast, recommended |
|
| 42 |
+
| [PART 1](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q5_K_S.gguf.part2of2) | Q5_K_S | 84.5 | |
|
| 43 |
+
| [PART 1](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q5_K_M.gguf.part2of2) | Q5_K_M | 86.6 | |
|
| 44 |
+
| [PART 1](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q6_K.gguf.part3of3) | Q6_K | 100.7 | very good quality |
|
| 45 |
+
| [PART 1](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/magnum-v4-123b-GGUF/resolve/main/magnum-v4-123b.Q8_0.gguf.part3of3) | Q8_0 | 130.4 | fast, best quality |
|
| 46 |
|
| 47 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 48 |
types (lower is better):
|