Hugging Face's logo

mradermacher
/
Llama_3.x_70b_Nethesis_V1.1-GGUF

Transformers
GGUF
English
mergekit
Merge
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
5acedd7
·
verified ·
1 Parent(s): 97d23a1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -31,7 +31,16 @@ more details, including on how to concatenate multi-part files.
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
 
 
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
 
 
 
 
 
35
 
36
  Here is a handy graph by ikawrakow comparing some lower-quality quant
37
  types (lower is better):
 
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
34
+ | [GGUF](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q2_K.gguf) | Q2_K | 26.5 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
37
+ | [GGUF](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
38
  | [GGUF](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
39
+ | [GGUF](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
42
+ | [PART 1](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
43
+ | [PART 1](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama_3.x_70b_Nethesis_V1.1-GGUF/resolve/main/Llama_3.x_70b_Nethesis_V1.1.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
44
 
45
  Here is a handy graph by ikawrakow comparing some lower-quality quant
46
  types (lower is better):