mradermacher
commited on
Commit
•
fe803ee
1
Parent(s):
b9d07c4
auto-patch README.md
Browse files
README.md
CHANGED
@@ -37,9 +37,19 @@ more details, including on how to concatenate multi-part files.
|
|
37 |
|
38 |
| Link | Type | Size/GB | Notes |
|
39 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
40 |
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.IQ3_S.gguf) | IQ3_S | 5.7 | beats Q3_K* |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.IQ3_M.gguf) | IQ3_M | 5.8 | |
|
|
|
|
|
|
|
42 |
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended |
|
|
|
|
|
|
|
|
|
43 |
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q8_0.gguf) | Q8_0 | 13.8 | fast, best quality |
|
44 |
|
45 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
37 |
|
38 |
| Link | Type | Size/GB | Notes |
|
39 |
|:-----|:-----|--------:|:------|
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q2_K.gguf) | Q2_K | 4.9 | |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.IQ3_XS.gguf) | IQ3_XS | 5.4 | |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q3_K_S.gguf) | Q3_K_S | 5.7 | |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.IQ3_S.gguf) | IQ3_S | 5.7 | beats Q3_K* |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.IQ3_M.gguf) | IQ3_M | 5.8 | |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q3_K_M.gguf) | Q3_K_M | 6.3 | lower quality |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q3_K_L.gguf) | Q3_K_L | 6.8 | |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.IQ4_XS.gguf) | IQ4_XS | 7.1 | |
|
48 |
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended |
|
49 |
+
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q4_K_M.gguf) | Q4_K_M | 7.9 | fast, recommended |
|
50 |
+
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q5_K_S.gguf) | Q5_K_S | 9.0 | |
|
51 |
+
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q5_K_M.gguf) | Q5_K_M | 9.2 | |
|
52 |
+
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q6_K.gguf) | Q6_K | 10.7 | very good quality |
|
53 |
| [GGUF](https://huggingface.co/mradermacher/GK-MoE-0.1-GGUF/resolve/main/GK-MoE-0.1.Q8_0.gguf) | Q8_0 | 13.8 | fast, best quality |
|
54 |
|
55 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|