Hugging Face's logo

mradermacher
/
Llama-3-70B-Instruct-norefusal-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
d3d9465
•
1 Parent(s): 7bbce19

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -30,8 +30,14 @@ more details, including on how to concatenate multi-part files.
30
  |:-----|:-----|--------:|:------|
31
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q2_K.gguf) | Q2_K | 26.5 | |
32
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
 
33
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.IQ3_M.gguf) | IQ3_M | 32.0 | |
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
 
 
 
35
  | [PART 1](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
36
  | [PART 1](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
37
 
 
30
  |:-----|:-----|--------:|:------|
31
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q2_K.gguf) | Q2_K | 26.5 | |
32
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
33
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
34
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.IQ3_M.gguf) | IQ3_M | 32.0 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
36
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
37
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
38
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
39
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
41
  | [PART 1](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
42
  | [PART 1](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama-3-70B-Instruct-norefusal-GGUF/resolve/main/Llama-3-70B-Instruct-norefusal.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
43