mradermacher commited on
Commit
bb2d916
·
verified ·
1 Parent(s): 44ec564

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -0
README.md CHANGED
@@ -34,7 +34,19 @@ more details, including on how to concatenate multi-part files.
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
 
 
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | vision supplement |
 
 
38
 
39
  Here is a handy graph by ikawrakow comparing some lower-quality quant
40
  types (lower is better):
 
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.Q2_K.gguf) | Q2_K | 0.8 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.Q3_K_S.gguf) | Q3_K_S | 0.9 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.Q3_K_L.gguf) | Q3_K_L | 1.0 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.IQ4_XS.gguf) | IQ4_XS | 1.0 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.Q5_K_S.gguf) | Q5_K_S | 1.2 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.Q5_K_M.gguf) | Q5_K_M | 1.2 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.Q6_K.gguf) | Q6_K | 1.4 | very good quality |
47
  | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | vision supplement |
48
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/JSONify-Flux-GGUF/resolve/main/JSONify-Flux.f16.gguf) | f16 | 3.2 | 16 bpw, overkill |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):