mradermacher commited on
Commit
8a7f3f7
1 Parent(s): 9722126

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -28,9 +28,19 @@ more details, including on how to concatenate multi-part files.
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
 
 
31
  | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
 
32
  | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.IQ3_M.gguf) | IQ3_M | 32.0 | |
 
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
 
 
 
 
34
  | [PART 1](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
35
 
36
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
28
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q2_K.gguf) | Q2_K | 26.5 | |
32
+ | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.IQ3_XS.gguf) | IQ3_XS | 29.4 | |
33
  | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
34
+ | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
35
  | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.IQ3_M.gguf) | IQ3_M | 32.0 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
37
+ | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.IQ4_XS.gguf) | IQ4_XS | 38.4 | |
39
  | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
43
+ | [PART 1](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
44
  | [PART 1](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/CabraLlama3-70b-GGUF/resolve/main/CabraLlama3-70b.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant