auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -33,7 +33,7 @@ static quants of https://huggingface.co/kawasumi/Tema_Q-R12.2
|
|
| 33 |
|
| 34 |
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Tema_Q-R12.2-GGUF).***
|
| 35 |
|
| 36 |
-
weighted/imatrix quants
|
| 37 |
## Usage
|
| 38 |
|
| 39 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
@@ -46,7 +46,17 @@ more details, including on how to concatenate multi-part files.
|
|
| 46 |
|
| 47 |
| Link | Type | Size/GB | Notes |
|
| 48 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 52 |
types (lower is better):
|
|
|
|
| 33 |
|
| 34 |
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Tema_Q-R12.2-GGUF).***
|
| 35 |
|
| 36 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Tema_Q-R12.2-i1-GGUF
|
| 37 |
## Usage
|
| 38 |
|
| 39 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
|
| 46 |
|
| 47 |
| Link | Type | Size/GB | Notes |
|
| 48 |
|:-----|:-----|--------:|:------|
|
| 49 |
+
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q2_K.gguf) | Q2_K | 3.9 | |
|
| 50 |
+
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q3_K_S.gguf) | Q3_K_S | 4.4 | |
|
| 51 |
+
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality |
|
| 52 |
+
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q3_K_L.gguf) | Q3_K_L | 5.2 | |
|
| 53 |
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
|
| 54 |
+
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended |
|
| 55 |
+
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q5_K_S.gguf) | Q5_K_S | 6.6 | |
|
| 56 |
+
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q5_K_M.gguf) | Q5_K_M | 6.7 | |
|
| 57 |
+
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q6_K.gguf) | Q6_K | 7.7 | very good quality |
|
| 58 |
+
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality |
|
| 59 |
+
| [GGUF](https://huggingface.co/mradermacher/Tema_Q-R12.2-GGUF/resolve/main/Tema_Q-R12.2.f16.gguf) | f16 | 18.6 | 16 bpw, overkill |
|
| 60 |
|
| 61 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 62 |
types (lower is better):
|