Hugging Face's logo

mradermacher
/
Keiana-L3-Test6.2-8B-18-GGUF

Transformers
GGUF
English
Merge
mergekit
lazymergekit
Kaoeiri/Keiana-L3-Test5.4-8B-10
Kaoeiri/Keiana-L3-Test4.7-8B-3
Kaoeiri/Keiana-L3-Test6-8B-16
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
6db89b5
•
1 Parent(s): f090522

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -39,11 +39,15 @@ more details, including on how to concatenate multi-part files.
39
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
 
 
42
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
43
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
 
45
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
46
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
 
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
 
39
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
41
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality |
44
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
46
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
48
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Keiana-L3-Test6.2-8B-18-GGUF/resolve/main/Keiana-L3-Test6.2-8B-18.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):