mradermacher commited on
Commit
feacb08
1 Parent(s): 9d58326

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md CHANGED
@@ -35,9 +35,24 @@ more details, including on how to concatenate multi-part files.
35
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
 
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q2_K.gguf) | i1-Q2_K | 4.1 | IQ3_XXS probably better |
39
  | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.3 | lower quality |
 
 
 
 
 
 
 
 
40
  | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.2 | optimal size/speed/quality |
 
 
 
 
41
 
42
  Here is a handy graph by ikawrakow comparing some lower-quality quant
43
  types (lower is better):
 
35
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
38
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.0 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.3 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.8 | |
41
  | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q2_K.gguf) | i1-Q2_K | 4.1 | IQ3_XXS probably better |
42
  | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.3 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.5 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.8 | IQ3_XS probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-IQ3_S.gguf) | i1-IQ3_S | 4.8 | beats Q3_K* |
46
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-IQ3_M.gguf) | i1-IQ3_M | 4.9 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.3 | IQ3_S probably better |
48
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.8 | IQ3_M probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.9 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q4_0.gguf) | i1-Q4_0 | 6.2 | fast, low quality |
51
  | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.2 | optimal size/speed/quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.6 | fast, recommended |
53
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.5 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 7.7 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/SnowLotus-v2-10.7B-i1-GGUF/resolve/main/SnowLotus-v2-10.7B.i1-Q6_K.gguf) | i1-Q6_K | 8.9 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant
58
  types (lower is better):