Hugging Face's logo

mradermacher
/
Llama-3-70B-japanese-suzume-vector-v0.1-GGUF

Transformers
GGUF
Japanese
English
llama3
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
4d10694
·
verified ·
1 Parent(s): 2639d9b

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -36,8 +36,11 @@ more details, including on how to concatenate multi-part files.
36
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
38
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
 
39
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
40
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
 
 
41
  | [PART 1](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
42
  | [PART 1](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
43
 
 
36
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
38
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.IQ4_XS.gguf) | IQ4_XS | 38.4 | |
40
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
44
  | [PART 1](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
45
  | [PART 1](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70B-japanese-suzume-vector-v0.1-GGUF/resolve/main/Llama-3-70B-japanese-suzume-vector-v0.1.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
46