Hugging Face's logo

mradermacher
/
EuroLLM-1.7B-GGUF

Transformers
GGUF
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
30d5004
·
verified ·
1 Parent(s): 0d2685e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -66,6 +66,7 @@ more details, including on how to concatenate multi-part files.
66
  | [GGUF](https://huggingface.co/mradermacher/EuroLLM-1.7B-GGUF/resolve/main/EuroLLM-1.7B.Q2_K.gguf) | Q2_K | 0.8 | |
67
  | [GGUF](https://huggingface.co/mradermacher/EuroLLM-1.7B-GGUF/resolve/main/EuroLLM-1.7B.IQ3_S.gguf) | IQ3_S | 0.9 | beats Q3_K* |
68
  | [GGUF](https://huggingface.co/mradermacher/EuroLLM-1.7B-GGUF/resolve/main/EuroLLM-1.7B.Q4_K_S.gguf) | Q4_K_S | 1.1 | fast, recommended |
 
69
  | [GGUF](https://huggingface.co/mradermacher/EuroLLM-1.7B-GGUF/resolve/main/EuroLLM-1.7B.f16.gguf) | f16 | 3.4 | 16 bpw, overkill |
70
 
71
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
66
  | [GGUF](https://huggingface.co/mradermacher/EuroLLM-1.7B-GGUF/resolve/main/EuroLLM-1.7B.Q2_K.gguf) | Q2_K | 0.8 | |
67
  | [GGUF](https://huggingface.co/mradermacher/EuroLLM-1.7B-GGUF/resolve/main/EuroLLM-1.7B.IQ3_S.gguf) | IQ3_S | 0.9 | beats Q3_K* |
68
  | [GGUF](https://huggingface.co/mradermacher/EuroLLM-1.7B-GGUF/resolve/main/EuroLLM-1.7B.Q4_K_S.gguf) | Q4_K_S | 1.1 | fast, recommended |
69
+ | [GGUF](https://huggingface.co/mradermacher/EuroLLM-1.7B-GGUF/resolve/main/EuroLLM-1.7B.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality |
70
  | [GGUF](https://huggingface.co/mradermacher/EuroLLM-1.7B-GGUF/resolve/main/EuroLLM-1.7B.f16.gguf) | f16 | 3.4 | 16 bpw, overkill |
71
 
72
  Here is a handy graph by ikawrakow comparing some lower-quality quant