Hugging Face's logo

mradermacher
/
Llama3.3-70B-CogniLink-GGUF

Text Generation
Transformers
GGUF
English
state-of-the-art
reasoning
chain-of-thought
llama
instruction-tuning
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
7a7b885
·
verified ·
1 Parent(s): 7acfc6f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -40,7 +40,14 @@ more details, including on how to concatenate multi-part files.
40
  | Link | Type | Size/GB | Notes |
41
  |:-----|:-----|--------:|:------|
42
  | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q2_K.gguf) | Q2_K | 26.5 | |
 
 
 
43
  | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
 
 
 
 
44
  | [PART 1](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
40
  | Link | Type | Size/GB | Notes |
41
  |:-----|:-----|--------:|:------|
42
  | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q2_K.gguf) | Q2_K | 26.5 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q3_K_S.gguf) | Q3_K_S | 31.0 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q3_K_L.gguf) | Q3_K_L | 37.2 | |
46
  | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q5_K_S.gguf) | Q5_K_S | 48.8 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q5_K_M.gguf) | Q5_K_M | 50.0 | |
50
+ | [PART 1](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality |
51
  | [PART 1](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Llama3.3-70B-CogniLink-GGUF/resolve/main/Llama3.3-70B-CogniLink.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant