Hugging Face's logo

mradermacher
/
Higgs-Llama-3-70B-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community
1
mradermacher commited on
Commit
fd21c43
·
verified ·
1 Parent(s): 31a70d9

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -30,8 +30,10 @@ more details, including on how to concatenate multi-part files.
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
 
33
  | [GGUF](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
34
  | [PART 1](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
 
35
 
36
  Here is a handy graph by ikawrakow comparing some lower-quality quant
37
  types (lower is better):
 
30
  | Link | Type | Size/GB | Notes |
31
  |:-----|:-----|--------:|:------|
32
  | [GGUF](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* |
33
+ | [GGUF](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.IQ3_M.gguf) | IQ3_M | 32.0 | |
34
  | [GGUF](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended |
35
  | [PART 1](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | fast, best quality |
36
+ | [PART 1](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.f16.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.f16.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Higgs-Llama-3-70B-GGUF/resolve/main/Higgs-Llama-3-70B.f16.gguf.part3of3) | f16 | 141.2 | 16 bpw, overkill |
37
 
38
  Here is a handy graph by ikawrakow comparing some lower-quality quant
39
  types (lower is better):