mradermacher
commited on
auto-patch README.md
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ tags:
|
|
22 |
static quants of https://huggingface.co/Daemontatox/RA_Reasoner2.0
|
23 |
|
24 |
<!-- provided-files -->
|
25 |
-
weighted/imatrix quants
|
26 |
## Usage
|
27 |
|
28 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -39,7 +39,14 @@ more details, including on how to concatenate multi-part files.
|
|
39 |
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q3_K_S.gguf) | Q3_K_S | 4.7 | |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q3_K_M.gguf) | Q3_K_M | 5.2 | lower quality |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q3_K_L.gguf) | Q3_K_L | 5.6 | |
|
|
|
42 |
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q4_K_S.gguf) | Q4_K_S | 6.1 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
|
44 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
45 |
types (lower is better):
|
|
|
22 |
static quants of https://huggingface.co/Daemontatox/RA_Reasoner2.0
|
23 |
|
24 |
<!-- provided-files -->
|
25 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/RA_Reasoner2.0-i1-GGUF
|
26 |
## Usage
|
27 |
|
28 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
39 |
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q3_K_S.gguf) | Q3_K_S | 4.7 | |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q3_K_M.gguf) | Q3_K_M | 5.2 | lower quality |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q3_K_L.gguf) | Q3_K_L | 5.6 | |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.IQ4_XS.gguf) | IQ4_XS | 5.8 | |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q4_K_S.gguf) | Q4_K_S | 6.1 | fast, recommended |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q4_K_M.gguf) | Q4_K_M | 6.4 | fast, recommended |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q5_K_S.gguf) | Q5_K_S | 7.2 | |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q5_K_M.gguf) | Q5_K_M | 7.4 | |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q6_K.gguf) | Q6_K | 8.6 | very good quality |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.Q8_0.gguf) | Q8_0 | 11.1 | fast, best quality |
|
49 |
+
| [GGUF](https://huggingface.co/mradermacher/RA_Reasoner2.0-GGUF/resolve/main/RA_Reasoner2.0.f16.gguf) | f16 | 20.7 | 16 bpw, overkill |
|
50 |
|
51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
52 |
types (lower is better):
|