Hugging Face's logo

mradermacher
/
llama-3-experiment-v1-9B-GGUF

Transformers
GGUF
PyTorch
English
meta
llama-3
mergekit
Merge
Inference Endpoints
conversational
Model card Files Community
1
mradermacher commited on
Commit
9027b56
·
verified ·
1 Parent(s): 2a0e0b0

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -40,10 +40,14 @@ more details, including on how to concatenate multi-part files.
40
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q3_K_S.gguf) | Q3_K_S | 4.1 | |
41
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q3_K_L.gguf) | Q3_K_L | 4.9 | |
 
43
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q4_K_S.gguf) | Q4_K_S | 5.3 | fast, recommended |
44
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended |
 
 
45
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q6_K.gguf) | Q6_K | 7.4 | very good quality |
46
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q8_0.gguf) | Q8_0 | 9.6 | fast, best quality |
 
47
 
48
  Here is a handy graph by ikawrakow comparing some lower-quality quant
49
  types (lower is better):
 
40
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q3_K_S.gguf) | Q3_K_S | 4.1 | |
41
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality |
42
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q3_K_L.gguf) | Q3_K_L | 4.9 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.IQ4_XS.gguf) | IQ4_XS | 5.1 | |
44
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q4_K_S.gguf) | Q4_K_S | 5.3 | fast, recommended |
45
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q4_K_M.gguf) | Q4_K_M | 5.5 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q5_K_S.gguf) | Q5_K_S | 6.3 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q5_K_M.gguf) | Q5_K_M | 6.4 | |
48
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q6_K.gguf) | Q6_K | 7.4 | very good quality |
49
  | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.Q8_0.gguf) | Q8_0 | 9.6 | fast, best quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/llama-3-experiment-v1-9B-GGUF/resolve/main/llama-3-experiment-v1-9B.f16.gguf) | f16 | 17.9 | 16 bpw, overkill |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):