mradermacher
commited on
Commit
•
84db509
1
Parent(s):
8918e2c
auto-patch README.md
Browse files
README.md
CHANGED
@@ -46,6 +46,7 @@ more details, including on how to concatenate multi-part files.
|
|
46 |
| Link | Type | Size/GB | Notes |
|
47 |
|:-----|:-----|--------:|:------|
|
48 |
| [GGUF](https://huggingface.co/mradermacher/calme-2.3-llama3-70b-GGUF/resolve/main/calme-2.3-llama3-70b.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
|
|
|
49 |
| [PART 1](https://huggingface.co/mradermacher/calme-2.3-llama3-70b-GGUF/resolve/main/calme-2.3-llama3-70b.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/calme-2.3-llama3-70b-GGUF/resolve/main/calme-2.3-llama3-70b.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
|
50 |
|
51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
46 |
| Link | Type | Size/GB | Notes |
|
47 |
|:-----|:-----|--------:|:------|
|
48 |
| [GGUF](https://huggingface.co/mradermacher/calme-2.3-llama3-70b-GGUF/resolve/main/calme-2.3-llama3-70b.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
|
49 |
+
| [GGUF](https://huggingface.co/mradermacher/calme-2.3-llama3-70b-GGUF/resolve/main/calme-2.3-llama3-70b.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
|
50 |
| [PART 1](https://huggingface.co/mradermacher/calme-2.3-llama3-70b-GGUF/resolve/main/calme-2.3-llama3-70b.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/calme-2.3-llama3-70b-GGUF/resolve/main/calme-2.3-llama3-70b.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
|
51 |
|
52 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|