mradermacher commited on
Commit
3eca255
1 Parent(s): eaf5bc0

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -0
README.md CHANGED
@@ -28,7 +28,20 @@ more details, including on how to concatenate multi-part files.
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
 
 
 
31
  | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
 
 
 
 
 
 
 
 
 
 
32
 
33
  Here is a handy graph by ikawrakow comparing some lower-quality quant
34
  types (lower is better):
 
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.Q2_K.gguf) | Q2_K | 2.8 | |
32
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
34
  | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
35
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.IQ3_M.gguf) | IQ3_M | 3.4 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
37
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/IceEspressoRPv2-7b-GGUF/resolve/main/IceEspressoRPv2-7b.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
47
  types (lower is better):