mradermacher
commited on
Commit
•
663983f
1
Parent(s):
283ecf1
auto-patch README.md
Browse files
README.md
CHANGED
@@ -33,6 +33,7 @@ more details, including on how to concatenate multi-part files.
|
|
33 |
| [GGUF](https://huggingface.co/mradermacher/tinyllama-15M-alpaca-finetuned-GGUF/resolve/main/tinyllama-15M-alpaca-finetuned.IQ3_S.gguf) | IQ3_S | 0.1 | beats Q3_K* |
|
34 |
| [GGUF](https://huggingface.co/mradermacher/tinyllama-15M-alpaca-finetuned-GGUF/resolve/main/tinyllama-15M-alpaca-finetuned.Q2_K.gguf) | Q2_K | 0.1 | |
|
35 |
| [GGUF](https://huggingface.co/mradermacher/tinyllama-15M-alpaca-finetuned-GGUF/resolve/main/tinyllama-15M-alpaca-finetuned.Q4_K_S.gguf) | Q4_K_S | 0.1 | fast, recommended |
|
|
|
36 |
| [GGUF](https://huggingface.co/mradermacher/tinyllama-15M-alpaca-finetuned-GGUF/resolve/main/tinyllama-15M-alpaca-finetuned.f16.gguf) | f16 | 0.1 | 16 bpw, overkill |
|
37 |
|
38 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
33 |
| [GGUF](https://huggingface.co/mradermacher/tinyllama-15M-alpaca-finetuned-GGUF/resolve/main/tinyllama-15M-alpaca-finetuned.IQ3_S.gguf) | IQ3_S | 0.1 | beats Q3_K* |
|
34 |
| [GGUF](https://huggingface.co/mradermacher/tinyllama-15M-alpaca-finetuned-GGUF/resolve/main/tinyllama-15M-alpaca-finetuned.Q2_K.gguf) | Q2_K | 0.1 | |
|
35 |
| [GGUF](https://huggingface.co/mradermacher/tinyllama-15M-alpaca-finetuned-GGUF/resolve/main/tinyllama-15M-alpaca-finetuned.Q4_K_S.gguf) | Q4_K_S | 0.1 | fast, recommended |
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/tinyllama-15M-alpaca-finetuned-GGUF/resolve/main/tinyllama-15M-alpaca-finetuned.Q8_0.gguf) | Q8_0 | 0.1 | fast, best quality |
|
37 |
| [GGUF](https://huggingface.co/mradermacher/tinyllama-15M-alpaca-finetuned-GGUF/resolve/main/tinyllama-15M-alpaca-finetuned.f16.gguf) | f16 | 0.1 | 16 bpw, overkill |
|
38 |
|
39 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|