Hugging Face's logo

mradermacher
/
L3-8B-Lunar-Stheno-i1-GGUF

Transformers
GGUF
English
nsfw
Not-For-All-Audiences
llama-3
text-generation-inference
mergekit
Merge
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
5656a78
•
1 Parent(s): 39660b0

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -21
README.md CHANGED
@@ -36,27 +36,27 @@ more details, including on how to concatenate multi-part files.
36
 
37
  | Link | Type | Size/GB | Notes |
38
  |:-----|:-----|--------:|:------|
39
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
40
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
41
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
42
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
43
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
44
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
45
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
46
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
47
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
48
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
49
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
50
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
51
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
52
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
53
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
54
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
55
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
56
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
57
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
58
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
59
- | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant
62
  types (lower is better):
 
36
 
37
  | Link | Type | Size/GB | Notes |
38
  |:-----|:-----|--------:|:------|
39
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
40
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
41
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
50
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
52
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
53
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
56
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
57
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/L3-8B-Lunar-Stheno-i1-GGUF/resolve/main/L3-8B-Lunar-Stheno.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant
62
  types (lower is better):