mradermacher
commited on
Commit
•
385165c
1
Parent(s):
66a3cb4
auto-patch README.md
Browse files
README.md
CHANGED
@@ -38,6 +38,7 @@ more details, including on how to concatenate multi-part files.
|
|
38 |
|:-----|:-----|--------:|:------|
|
39 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | |
|
|
|
41 |
|
42 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
43 |
types (lower is better):
|
|
|
38 |
|:-----|:-----|--------:|:------|
|
39 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-1.5B-Instruct-i1-GGUF/resolve/main/Qwen2.5-Coder-1.5B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality |
|
42 |
|
43 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
44 |
types (lower is better):
|