mradermacher commited on
Commit
a27c501
·
verified ·
1 Parent(s): 135ef45

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -30,7 +30,15 @@ more details, including on how to concatenate multi-part files.
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q2_K.gguf) | Q2_K | 6.4 | |
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q4_K_S.gguf) | Q4_K_S | 9.4 | fast, recommended |
 
 
 
 
 
 
34
 
35
  Here is a handy graph by ikawrakow comparing some lower-quality quant
36
  types (lower is better):
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q2_K.gguf) | Q2_K | 6.4 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q3_K_S.gguf) | Q3_K_S | 7.2 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q3_K_M.gguf) | Q3_K_M | 8.5 | lower quality |
35
  | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q4_K_S.gguf) | Q4_K_S | 9.4 | fast, recommended |
36
+ | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q3_K_L.gguf) | Q3_K_L | 9.4 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q4_K_M.gguf) | Q4_K_M | 10.2 | fast, recommended |
38
+ | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q5_K_S.gguf) | Q5_K_S | 11.2 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q5_K_M.gguf) | Q5_K_M | 11.8 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q6_K.gguf) | Q6_K | 13.2 | very good quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/NL2SQL-StarCoder-15B-GGUF/resolve/main/NL2SQL-StarCoder-15B.Q8_0.gguf) | Q8_0 | 17.1 | fast, best quality |
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
44
  types (lower is better):