mradermacher commited on
Commit
1ddbf4e
·
verified ·
1 Parent(s): c994e47

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -0
README.md CHANGED
@@ -30,14 +30,30 @@ more details, including on how to concatenate multi-part files.
30
 
31
  | Link | Type | Size/GB | Notes |
32
  |:-----|:-----|--------:|:------|
 
 
 
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
 
34
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
35
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
 
 
 
36
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
37
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
 
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.2 | prefer IQ4_XS |
39
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
40
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
 
 
 
 
41
 
42
  Here is a handy graph by ikawrakow comparing some lower-quality quant
43
  types (lower is better):
 
30
 
31
  | Link | Type | Size/GB | Notes |
32
  |:-----|:-----|--------:|:------|
33
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate |
34
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate |
35
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | |
38
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.6 | very low quality |
40
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better |
41
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality |
42
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better |
44
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* |
45
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | |
46
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better |
48
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality |
50
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.2 | prefer IQ4_XS |
51
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality |
52
  | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended |
53
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q4_1.gguf) | i1-Q4_1 | 4.7 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/haryra-7b-mistral-id-i1-GGUF/resolve/main/haryra-7b-mistral-id.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | practically like static Q6_K |
57
 
58
  Here is a handy graph by ikawrakow comparing some lower-quality quant
59
  types (lower is better):