mradermacher
commited on
Commit
•
558be8a
1
Parent(s):
8167bae
auto-patch README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ tags:
|
|
21 |
static quants of https://huggingface.co/powermove72/Elysium2.1-11b
|
22 |
|
23 |
<!-- provided-files -->
|
24 |
-
weighted/imatrix quants
|
25 |
## Usage
|
26 |
|
27 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -34,9 +34,19 @@ more details, including on how to concatenate multi-part files.
|
|
34 |
|
35 |
| Link | Type | Size/GB | Notes |
|
36 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
37 |
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.IQ3_S.gguf) | IQ3_S | 5.0 | beats Q3_K* |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.IQ3_M.gguf) | IQ3_M | 5.1 | |
|
|
|
|
|
|
|
39 |
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q4_K_S.gguf) | Q4_K_S | 6.5 | fast, recommended |
|
|
|
|
|
|
|
|
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q8_0.gguf) | Q8_0 | 12.0 | fast, best quality |
|
41 |
|
42 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
21 |
static quants of https://huggingface.co/powermove72/Elysium2.1-11b
|
22 |
|
23 |
<!-- provided-files -->
|
24 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF
|
25 |
## Usage
|
26 |
|
27 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
34 |
|
35 |
| Link | Type | Size/GB | Notes |
|
36 |
|:-----|:-----|--------:|:------|
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q2_K.gguf) | Q2_K | 4.3 | |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.IQ3_XS.gguf) | IQ3_XS | 4.7 | |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q3_K_S.gguf) | Q3_K_S | 5.0 | |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.IQ3_S.gguf) | IQ3_S | 5.0 | beats Q3_K* |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.IQ3_M.gguf) | IQ3_M | 5.1 | |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q3_K_M.gguf) | Q3_K_M | 5.5 | lower quality |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q3_K_L.gguf) | Q3_K_L | 6.0 | |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.IQ4_XS.gguf) | IQ4_XS | 6.2 | |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q4_K_S.gguf) | Q4_K_S | 6.5 | fast, recommended |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q4_K_M.gguf) | Q4_K_M | 6.8 | fast, recommended |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q5_K_S.gguf) | Q5_K_S | 7.8 | |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q5_K_M.gguf) | Q5_K_M | 8.0 | |
|
49 |
+
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q6_K.gguf) | Q6_K | 9.3 | very good quality |
|
50 |
| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF/resolve/main/Elysium2.1-11b.Q8_0.gguf) | Q8_0 | 12.0 | fast, best quality |
|
51 |
|
52 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|