mradermacher commited on
Commit
ffbdcec
·
verified ·
1 Parent(s): ec01dff

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -38,7 +38,15 @@ more details, including on how to concatenate multi-part files.
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
  | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.Q2_K.gguf) | Q2_K | 2.8 | |
 
 
 
41
  | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
 
 
 
 
 
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
44
  types (lower is better):
 
38
  | Link | Type | Size/GB | Notes |
39
  |:-----|:-----|--------:|:------|
40
  | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.Q2_K.gguf) | Q2_K | 2.8 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
44
  | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Mistral-portuguese-luana-7b-chat-GGUF/resolve/main/Mistral-portuguese-luana-7b-chat.f16.gguf) | f16 | 14.6 | 16 bpw, overkill |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):