Hugging Face's logo

mradermacher
/
oh_v1.3_slim_orca_x8-GGUF

Transformers
GGUF
English
llama-factory
full
Generated from Trainer
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
0bc6b2d
·
verified ·
1 Parent(s): 2f99eac

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -37,8 +37,14 @@ more details, including on how to concatenate multi-part files.
37
  | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
38
  | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
 
40
  | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
 
 
 
41
  | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
 
 
42
 
43
  Here is a handy graph by ikawrakow comparing some lower-quality quant
44
  types (lower is better):
 
37
  | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
38
  | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
39
  | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
41
  | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
45
  | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/oh_v1.3_slim_orca_x8-GGUF/resolve/main/oh_v1.3_slim_orca_x8.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
48
 
49
  Here is a handy graph by ikawrakow comparing some lower-quality quant
50
  types (lower is better):