Commit
•
77c828d
1
Parent(s):
21c1e45
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -36,7 +36,15 @@ more details, including on how to concatenate multi-part files.
|
|
| 36 |
| Link | Type | Size/GB | Notes |
|
| 37 |
|:-----|:-----|--------:|:------|
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q2_K.gguf) | Q2_K | 4.9 | |
|
|
|
|
|
|
|
|
|
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 42 |
types (lower is better):
|
|
|
|
| 36 |
| Link | Type | Size/GB | Notes |
|
| 37 |
|:-----|:-----|--------:|:------|
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q2_K.gguf) | Q2_K | 4.9 | |
|
| 39 |
+
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q3_K_S.gguf) | Q3_K_S | 5.7 | |
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q3_K_M.gguf) | Q3_K_M | 6.3 | lower quality |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q3_K_L.gguf) | Q3_K_L | 6.8 | |
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q4_K_M.gguf) | Q4_K_M | 7.9 | fast, recommended |
|
| 44 |
+
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q5_K_S.gguf) | Q5_K_S | 9.0 | |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q5_K_M.gguf) | Q5_K_M | 9.2 | |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q6_K.gguf) | Q6_K | 10.7 | very good quality |
|
| 47 |
+
| [GGUF](https://huggingface.co/mradermacher/MixtureofMerges-MoE-2x7b-v0.01b-DELLA-GGUF/resolve/main/MixtureofMerges-MoE-2x7b-v0.01b-DELLA.Q8_0.gguf) | Q8_0 | 13.8 | fast, best quality |
|
| 48 |
|
| 49 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 50 |
types (lower is better):
|