mradermacher commited on
Commit
b457354
·
verified ·
1 Parent(s): aa28948

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -85,7 +85,7 @@ tags:
85
  static quants of https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
86
 
87
  <!-- provided-files -->
88
- 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.
89
  ## Usage
90
 
91
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -102,9 +102,11 @@ more details, including on how to concatenate multi-part files.
102
  | [GGUF](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q3_K_S.gguf) | Q3_K_S | 46.8 | |
103
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q3_K_M.gguf.part2of2) | Q3_K_M | 51.9 | lower quality |
104
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q3_K_L.gguf.part2of2) | Q3_K_L | 56.1 | |
 
105
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q4_K_S.gguf.part2of2) | Q4_K_S | 61.6 | fast, recommended |
106
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q4_K_M.gguf.part2of2) | Q4_K_M | 65.5 | fast, recommended |
107
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q5_K_S.gguf.part2of2) | Q5_K_S | 74.4 | |
 
108
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q6_K.gguf.part2of2) | Q6_K | 88.5 | very good quality |
109
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q8_0.gguf.part3of3) | Q8_0 | 114.6 | fast, best quality |
110
 
 
85
  static quants of https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
86
 
87
  <!-- provided-files -->
88
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-i1-GGUF
89
  ## Usage
90
 
91
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
102
  | [GGUF](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q3_K_S.gguf) | Q3_K_S | 46.8 | |
103
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q3_K_M.gguf.part2of2) | Q3_K_M | 51.9 | lower quality |
104
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q3_K_L.gguf.part2of2) | Q3_K_L | 56.1 | |
105
+ | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.IQ4_XS.gguf.part2of2) | IQ4_XS | 58.4 | |
106
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q4_K_S.gguf.part2of2) | Q4_K_S | 61.6 | fast, recommended |
107
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q4_K_M.gguf.part2of2) | Q4_K_M | 65.5 | fast, recommended |
108
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q5_K_S.gguf.part2of2) | Q5_K_S | 74.4 | |
109
+ | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q5_K_M.gguf.part2of2) | Q5_K_M | 76.6 | |
110
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q6_K.gguf.part2of2) | Q6_K | 88.5 | very good quality |
111
  | [PART 1](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Llama-4-Scout-17B-16E-Instruct-GGUF/resolve/main/Llama-4-Scout-17B-16E-Instruct.Q8_0.gguf.part3of3) | Q8_0 | 114.6 | fast, best quality |
112