mradermacher commited on
Commit
a19173d
·
verified ·
1 Parent(s): 59f24d1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -39,8 +39,11 @@ more details, including on how to concatenate multi-part files.
39
  | Link | Type | Size/GB | Notes |
40
  |:-----|:-----|--------:|:------|
41
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) |
 
42
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-IQ1_M.gguf) | i1-IQ1_M | 7.0 | mostly desperate |
43
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.1 | |
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-IQ2_M.gguf) | i1-IQ2_M | 10.0 | |
45
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-Q2_K_S.gguf) | i1-Q2_K_S | 10.3 | very low quality |
46
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-Q2_K.gguf) | i1-Q2_K | 11.1 | IQ3_XXS probably better |
@@ -52,6 +55,7 @@ more details, including on how to concatenate multi-part files.
52
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.1 | |
53
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.2 | optimal size/speed/quality |
54
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.2 | fast, recommended |
 
55
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-Q6_K.gguf) | i1-Q6_K | 24.7 | practically like static Q6_K |
56
 
57
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
39
  | Link | Type | Size/GB | Notes |
40
  |:-----|:-----|--------:|:------|
41
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) |
42
+ | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-IQ1_S.gguf) | i1-IQ1_S | 6.3 | for the desperate |
43
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-IQ1_M.gguf) | i1-IQ1_M | 7.0 | mostly desperate |
44
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.1 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.0 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-IQ2_S.gguf) | i1-IQ2_S | 9.1 | |
47
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-IQ2_M.gguf) | i1-IQ2_M | 10.0 | |
48
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-Q2_K_S.gguf) | i1-Q2_K_S | 10.3 | very low quality |
49
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-Q2_K.gguf) | i1-Q2_K | 11.1 | IQ3_XXS probably better |
 
55
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-IQ4_XS.gguf) | i1-IQ4_XS | 16.1 | |
56
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-Q4_K_S.gguf) | i1-Q4_K_S | 17.2 | optimal size/speed/quality |
57
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-Q4_K_M.gguf) | i1-Q4_K_M | 18.2 | fast, recommended |
58
+ | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-Q5_K_S.gguf) | i1-Q5_K_S | 20.8 | |
59
  | [GGUF](https://huggingface.co/mradermacher/GLM-4.7-Flash-i1-GGUF/resolve/main/GLM-4.7-Flash.i1-Q6_K.gguf) | i1-Q6_K | 24.7 | practically like static Q6_K |
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant