mradermacher
commited on
Commit
•
db2238f
1
Parent(s):
4441a1e
auto-patch README.md
Browse files
README.md
CHANGED
@@ -31,9 +31,13 @@ more details, including on how to concatenate multi-part files.
|
|
31 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
|
32 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
|
33 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
|
|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
|
|
|
|
|
35 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
|
36 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
|
|
|
37 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
|
38 |
|
39 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
31 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
|
32 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
|
33 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
|
34 |
+
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
|
35 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
|
39 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/Tess-2.0-Llama-3-8B-i1-GGUF/resolve/main/Tess-2.0-Llama-3-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
|
42 |
|
43 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|