Hugging Face's logo

mradermacher
/
PLLuM-12B-base-250801-GGUF

Transformers
GGUF
Polish
Model card Files
xet
Community
mradermacher commited on
Commit
5fcaf16
·
verified ·
1 Parent(s): 03ba08c

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -38,8 +38,16 @@ more details, including on how to concatenate multi-part files.
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
  | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q2_K.gguf) | Q2_K | 4.9 | |
 
41
  | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality |
 
 
42
  | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended |
 
 
 
 
 
43
 
44
  Here is a handy graph by ikawrakow comparing some lower-quality quant
45
  types (lower is better):
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
  | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q2_K.gguf) | Q2_K | 4.9 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q3_K_S.gguf) | Q3_K_S | 5.6 | |
42
  | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q3_K_L.gguf) | Q3_K_L | 6.7 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.IQ4_XS.gguf) | IQ4_XS | 6.9 | |
45
  | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q5_K_S.gguf) | Q5_K_S | 8.6 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q5_K_M.gguf) | Q5_K_M | 8.8 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q6_K.gguf) | Q6_K | 10.2 | very good quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-250801-GGUF/resolve/main/PLLuM-12B-base-250801.Q8_0.gguf) | Q8_0 | 13.1 | fast, best quality |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):