auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -40,7 +40,7 @@ static quants of https://huggingface.co/NousResearch/Hermes-4-70B
|
|
| 40 |
|
| 41 |
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hermes-4-70B-GGUF).***
|
| 42 |
|
| 43 |
-
weighted/imatrix quants
|
| 44 |
## Usage
|
| 45 |
|
| 46 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
@@ -57,9 +57,11 @@ more details, including on how to concatenate multi-part files.
|
|
| 57 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
|
| 58 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
|
| 59 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
|
|
|
|
| 60 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
|
| 61 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
|
| 62 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
|
|
|
|
| 63 |
| [PART 1](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
|
| 64 |
| [PART 1](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
|
| 65 |
|
|
|
|
| 40 |
|
| 41 |
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hermes-4-70B-GGUF).***
|
| 42 |
|
| 43 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Hermes-4-70B-i1-GGUF
|
| 44 |
## Usage
|
| 45 |
|
| 46 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
|
| 57 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
|
| 58 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
|
| 59 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
|
| 60 |
+
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.IQ4_XS.gguf) | IQ4_XS | 38.4 | |
|
| 61 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
|
| 62 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
|
| 63 |
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
|
| 64 |
+
| [GGUF](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
|
| 65 |
| [PART 1](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
|
| 66 |
| [PART 1](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Hermes-4-70B-GGUF/resolve/main/Hermes-4-70B.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
|
| 67 |
|