Commit
•
9f8c3c5
1
Parent(s):
156b48a
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -28,11 +28,15 @@ more details, including on how to concatenate multi-part files.
|
|
| 28 |
|
| 29 |
| Link | Type | Size/GB | Notes |
|
| 30 |
|:-----|:-----|--------:|:------|
|
|
|
|
| 31 |
| [GGUF](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q2_K.gguf) | i1-Q2_K | 45.1 | IQ3_XXS probably better |
|
| 32 |
| [GGUF](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 47.1 | lower quality |
|
|
|
|
| 33 |
| [PART 1](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 58.8 | IQ3_S probably better |
|
|
|
|
| 34 |
| [PART 1](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 69.2 | optimal size/speed/quality |
|
| 35 |
| [PART 1](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 73.1 | fast, recommended |
|
|
|
|
| 36 |
|
| 37 |
|
| 38 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
|
| 28 |
|
| 29 |
| Link | Type | Size/GB | Notes |
|
| 30 |
|:-----|:-----|--------:|:------|
|
| 31 |
+
| [GGUF](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-IQ2_M.gguf) | i1-IQ2_M | 41.4 | |
|
| 32 |
| [GGUF](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q2_K.gguf) | i1-Q2_K | 45.1 | IQ3_XXS probably better |
|
| 33 |
| [GGUF](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 47.1 | lower quality |
|
| 34 |
+
| [PART 1](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q3_K_S.gguf.part2of2) | i1-Q3_K_S | 52.7 | IQ3_XS probably better |
|
| 35 |
| [PART 1](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 58.8 | IQ3_S probably better |
|
| 36 |
+
| [PART 1](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 65.1 | |
|
| 37 |
| [PART 1](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 69.2 | optimal size/speed/quality |
|
| 38 |
| [PART 1](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 73.1 | fast, recommended |
|
| 39 |
+
| [PART 1](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/athena-120b-i1-GGUF/resolve/main/athena-120b.i1-Q6_K.gguf.part3of3) | i1-Q6_K | 99.6 | practically like static Q6_K |
|
| 40 |
|
| 41 |
|
| 42 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|