Hugging Face's logo

mradermacher
/
LCARS_AI_1x2_001_SuperAI-GGUF

Transformers
GGUF
English
Mixture of Experts
Merge
sft
trl
law
code
cyber
medical
bio
Cyber-Series
Mixture-Of-Experts
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
e3c380f
·
verified ·
1 Parent(s): 7af364b

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -42,7 +42,17 @@ more details, including on how to concatenate multi-part files.
42
  | Link | Type | Size/GB | Notes |
43
  |:-----|:-----|--------:|:------|
44
  | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q2_K.gguf) | Q2_K | 4.9 | |
 
 
 
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended |
 
 
 
 
 
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):
 
42
  | Link | Type | Size/GB | Notes |
43
  |:-----|:-----|--------:|:------|
44
  | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q2_K.gguf) | Q2_K | 4.9 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q3_K_S.gguf) | Q3_K_S | 5.7 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q3_K_M.gguf) | Q3_K_M | 6.3 | lower quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q3_K_L.gguf) | Q3_K_L | 6.8 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.IQ4_XS.gguf) | IQ4_XS | 7.1 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q4_0_4_4.gguf) | Q4_0_4_4 | 7.4 | fast on arm, low quality |
50
  | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q4_K_S.gguf) | Q4_K_S | 7.4 | fast, recommended |
51
+ | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q4_K_M.gguf) | Q4_K_M | 7.9 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q5_K_S.gguf) | Q5_K_S | 9.0 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q5_K_M.gguf) | Q5_K_M | 9.2 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q6_K.gguf) | Q6_K | 10.7 | very good quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/LCARS_AI_1x2_001_SuperAI-GGUF/resolve/main/LCARS_AI_1x2_001_SuperAI.Q8_0.gguf) | Q8_0 | 13.8 | fast, best quality |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant
58
  types (lower is better):