Hugging Face's logo

mradermacher
/
MythoMix-L2-13b-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
Model card Files Community
mradermacher commited on
Commit
94b7100
·
verified ·
1 Parent(s): bc23e1e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -0
README.md CHANGED
@@ -29,8 +29,27 @@ more details, including on how to concatenate multi-part files.
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
32
  | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better |
 
 
 
 
 
 
 
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.5 | optimal size/speed/quality |
 
 
 
 
34
 
35
  Here is a handy graph by ikawrakow comparing some lower-quality quant
36
  types (lower is better):
 
29
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-IQ1_S.gguf) | i1-IQ1_S | 3.0 | for the desperate |
33
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-IQ1_M.gguf) | i1-IQ1_M | 3.2 | mostly desperate |
34
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.6 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-IQ2_S.gguf) | i1-IQ2_S | 4.3 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-IQ2_M.gguf) | i1-IQ2_M | 4.6 | |
38
  | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better |
39
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.1 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.5 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-IQ3_S.gguf) | i1-IQ3_S | 5.8 | beats Q3_K* |
42
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.8 | IQ3_XS probably better |
43
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-IQ3_M.gguf) | i1-IQ3_M | 6.1 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.4 | IQ3_S probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.0 | IQ3_M probably better |
46
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.1 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q4_0.gguf) | i1-Q4_0 | 7.5 | fast, low quality |
48
  | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.5 | optimal size/speed/quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.0 | fast, recommended |
50
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.1 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.3 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/MythoMix-L2-13b-i1-GGUF/resolve/main/MythoMix-L2-13b.i1-Q6_K.gguf) | i1-Q6_K | 10.8 | practically like static Q6_K |
53
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):