Hugging Face's logo

mradermacher
/
Quintellect-10.7B-i1-GGUF

Transformers
GGUF
English
code
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
dcc6881
·
verified ·
1 Parent(s): 1ec49c4

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -33,21 +33,30 @@ more details, including on how to concatenate multi-part files.
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
 
36
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.7 | mostly desperate |
37
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.0 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.3 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ2_S.gguf) | i1-IQ2_S | 3.5 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.8 | |
 
41
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q2_K.gguf) | i1-Q2_K | 4.1 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.3 | lower quality |
 
43
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.8 | IQ3_XS probably better |
 
44
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ3_M.gguf) | i1-IQ3_M | 4.9 | |
45
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.3 | IQ3_S probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.8 | IQ3_M probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.9 | |
 
 
 
 
48
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.2 | optimal size/speed/quality |
49
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.6 | fast, recommended |
50
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.5 | |
 
51
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q6_K.gguf) | i1-Q6_K | 8.9 | practically like static Q6_K |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
36
+ | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate |
37
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.7 | mostly desperate |
38
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.0 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.3 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ2_S.gguf) | i1-IQ2_S | 3.5 | |
41
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.8 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.8 | very low quality |
43
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q2_K.gguf) | i1-Q2_K | 4.1 | IQ3_XXS probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.3 | lower quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.5 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.8 | IQ3_XS probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ3_S.gguf) | i1-IQ3_S | 4.8 | beats Q3_K* |
48
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ3_M.gguf) | i1-IQ3_M | 4.9 | |
49
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.3 | IQ3_S probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.8 | IQ3_M probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.9 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 6.2 | fast on arm, low quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 6.2 | fast on arm+i8mm, low quality |
54
+ | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 6.2 | fast on arm+sve, low quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q4_0.gguf) | i1-Q4_0 | 6.2 | fast, low quality |
56
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.2 | optimal size/speed/quality |
57
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.6 | fast, recommended |
58
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.5 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 7.7 | |
60
  | [GGUF](https://huggingface.co/mradermacher/Quintellect-10.7B-i1-GGUF/resolve/main/Quintellect-10.7B.i1-Q6_K.gguf) | i1-Q6_K | 8.9 | practically like static Q6_K |
61
 
62
  Here is a handy graph by ikawrakow comparing some lower-quality quant