Hugging Face's logo

mradermacher
/
Llama-3-8B-UltraMedical-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
7992d83
·
verified ·
1 Parent(s): 6ac23d6

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -34,7 +34,15 @@ more details, including on how to concatenate multi-part files.
34
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q2_K.gguf) | Q2_K | 3.3 | |
35
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
 
 
 
 
 
 
38
 
39
  Here is a handy graph by ikawrakow comparing some lower-quality quant
40
  types (lower is better):
 
34
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q2_K.gguf) | Q2_K | 3.3 | |
35
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
36
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
37
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
39
  | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-UltraMedical-GGUF/resolve/main/Llama-3-8B-UltraMedical.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):