Hugging Face's logo

mradermacher
/
L3.1-Goldv4-10B-GGUF

Transformers
GGUF
English
mergekit
Merge
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
f19190b
·
verified ·
1 Parent(s): 43ba89f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -35,10 +35,14 @@ more details, including on how to concatenate multi-part files.
35
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q3_K_S.gguf) | Q3_K_S | 4.9 | |
36
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q3_K_M.gguf) | Q3_K_M | 5.4 | lower quality |
37
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q3_K_L.gguf) | Q3_K_L | 5.8 | |
 
38
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q4_K_S.gguf) | Q4_K_S | 6.3 | fast, recommended |
 
39
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q5_K_S.gguf) | Q5_K_S | 7.5 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q6_K.gguf) | Q6_K | 8.8 | very good quality |
41
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q8_0.gguf) | Q8_0 | 11.4 | fast, best quality |
 
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
44
  types (lower is better):
 
35
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q3_K_S.gguf) | Q3_K_S | 4.9 | |
36
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q3_K_M.gguf) | Q3_K_M | 5.4 | lower quality |
37
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q3_K_L.gguf) | Q3_K_L | 5.8 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.IQ4_XS.gguf) | IQ4_XS | 6.0 | |
39
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q4_K_S.gguf) | Q4_K_S | 6.3 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended |
41
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q5_K_S.gguf) | Q5_K_S | 7.5 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q5_K_M.gguf) | Q5_K_M | 7.7 | |
43
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q6_K.gguf) | Q6_K | 8.8 | very good quality |
44
  | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.Q8_0.gguf) | Q8_0 | 11.4 | fast, best quality |
45
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Goldv4-10B-GGUF/resolve/main/L3.1-Goldv4-10B.f16.gguf) | f16 | 21.4 | 16 bpw, overkill |
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):