mradermacher
commited on
Commit
•
d7af03a
1
Parent(s):
991a203
auto-patch README.md
Browse files
README.md
CHANGED
@@ -29,7 +29,7 @@ tags:
|
|
29 |
static quants of https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B
|
30 |
|
31 |
<!-- provided-files -->
|
32 |
-
weighted/imatrix quants
|
33 |
## Usage
|
34 |
|
35 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -43,9 +43,16 @@ more details, including on how to concatenate multi-part files.
|
|
43 |
| Link | Type | Size/GB | Notes |
|
44 |
|:-----|:-----|--------:|:------|
|
45 |
| [PART 1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q2_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q2_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q2_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q2_K.gguf.part4of4) | Q2_K | 149.4 | |
|
|
|
46 |
| [PART 1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_S.gguf.part4of4) | IQ3_S | 175.6 | beats Q3_K* |
|
47 |
| [PART 1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_M.gguf.part4of4) | IQ3_M | 181.8 | |
|
|
|
|
|
48 |
| [P1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_S.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_S.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_S.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_S.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_S.gguf.part5of5) | Q4_K_S | 230.6 | fast, recommended |
|
|
|
|
|
|
|
|
|
49 |
| [P1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part1of9) [P2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part2of9) [P3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part3of9) [P4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part4of9) [P5](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part5of9) [P6](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part6of9) [P7](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part7of9) [P8](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part8of9) [P9](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part9of9) | Q8_0 | 431.3 | fast, best quality |
|
50 |
|
51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
29 |
static quants of https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B
|
30 |
|
31 |
<!-- provided-files -->
|
32 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-i1-GGUF
|
33 |
## Usage
|
34 |
|
35 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
43 |
| Link | Type | Size/GB | Notes |
|
44 |
|:-----|:-----|--------:|:------|
|
45 |
| [PART 1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q2_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q2_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q2_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q2_K.gguf.part4of4) | Q2_K | 149.4 | |
|
46 |
+
| [PART 1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_S.gguf.part4of4) | Q3_K_S | 175.3 | |
|
47 |
| [PART 1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_S.gguf.part4of4) | IQ3_S | 175.6 | beats Q3_K* |
|
48 |
| [PART 1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.IQ3_M.gguf.part4of4) | IQ3_M | 181.8 | |
|
49 |
+
| [PART 1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_M.gguf.part4of4) | Q3_K_M | 195.5 | lower quality |
|
50 |
+
| [P1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_L.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_L.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_L.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_L.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q3_K_L.gguf.part5of5) | Q3_K_L | 212.9 | |
|
51 |
| [P1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_S.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_S.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_S.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_S.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_S.gguf.part5of5) | Q4_K_S | 230.6 | fast, recommended |
|
52 |
+
| [P1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_M.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_M.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_M.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_M.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q4_K_M.gguf.part5of5) | Q4_K_M | 243.2 | fast, recommended |
|
53 |
+
| [P1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_S.gguf.part1of6) [P2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_S.gguf.part2of6) [P3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_S.gguf.part3of6) [P4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_S.gguf.part4of6) [P5](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_S.gguf.part5of6) [P6](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_S.gguf.part6of6) | Q5_K_S | 279.4 | |
|
54 |
+
| [P1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_M.gguf.part1of6) [P2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_M.gguf.part2of6) [P3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_M.gguf.part3of6) [P4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_M.gguf.part4of6) [P5](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_M.gguf.part5of6) [P6](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q5_K_M.gguf.part6of6) | Q5_K_M | 286.7 | |
|
55 |
+
| [P1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q6_K.gguf.part1of7) [P2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q6_K.gguf.part2of7) [P3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q6_K.gguf.part3of7) [P4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q6_K.gguf.part4of7) [P5](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q6_K.gguf.part5of7) [P6](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q6_K.gguf.part6of7) [P7](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q6_K.gguf.part7of7) | Q6_K | 333.0 | very good quality |
|
56 |
| [P1](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part1of9) [P2](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part2of9) [P3](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part3of9) [P4](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part4of9) [P5](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part5of9) [P6](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part6of9) [P7](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part7of9) [P8](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part8of9) [P9](https://huggingface.co/mradermacher/Hermes-3-Llama-3.1-405B-GGUF/resolve/main/Hermes-3-Llama-3.1-405B.Q8_0.gguf.part9of9) | Q8_0 | 431.3 | fast, best quality |
|
57 |
|
58 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|