mradermacher commited on
Commit
9047d95
1 Parent(s): 8e9aac9

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -18,7 +18,7 @@ tags:
18
  static quants of https://huggingface.co/terrycraddock/Reflection-Llama-3.1-8B
19
 
20
  <!-- provided-files -->
21
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
22
  ## Usage
23
 
24
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -31,20 +31,20 @@ more details, including on how to concatenate multi-part files.
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q2_K.gguf) | Q2_K | 6.5 | |
35
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ3_XS.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ3_XS.gguf) | IQ3_XS | 7.1 | |
36
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 7.4 | |
37
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ3_S.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ3_S.gguf) | IQ3_S | 7.5 | beats Q3_K* |
38
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ3_M.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ3_M.gguf) | IQ3_M | 7.7 | |
39
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 8.1 | lower quality |
40
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 8.7 | |
41
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 9.1 | |
42
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 9.5 | fast, recommended |
43
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 9.9 | fast, recommended |
44
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 11.3 | |
45
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 11.6 | |
46
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q6_K.gguf) | Q6_K | 13.3 | very good quality |
47
- | [PART 1](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q8_0.gguf) [PART 2](https://huggingface.co/mradermacher/reflection-llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q8_0.gguf) | Q8_0 | 17.2 | fast, best quality |
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):
 
18
  static quants of https://huggingface.co/terrycraddock/Reflection-Llama-3.1-8B
19
 
20
  <!-- provided-files -->
21
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-i1-GGUF
22
  ## Usage
23
 
24
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q2_K.gguf) | Q2_K | 6.5 | |
35
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ3_XS.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ3_XS.gguf) | IQ3_XS | 7.1 | |
36
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 7.4 | |
37
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ3_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ3_S.gguf) | IQ3_S | 7.5 | beats Q3_K* |
38
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ3_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ3_M.gguf) | IQ3_M | 7.7 | |
39
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 8.1 | lower quality |
40
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 8.7 | |
41
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 9.1 | |
42
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 9.5 | fast, recommended |
43
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 9.9 | fast, recommended |
44
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 11.3 | |
45
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 11.6 | |
46
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q6_K.gguf) | Q6_K | 13.3 | very good quality |
47
+ | [PART 1](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/Reflection-Llama-3.1-8B.Q8_0.gguf) [PART 2](https://huggingface.co/mradermacher/Reflection-Llama-3.1-8B-GGUF/resolve/main/reflection-llama-3.1-8B.Q8_0.gguf) | Q8_0 | 17.2 | fast, best quality |
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):