Hugging Face's logo

mradermacher
/
Mixtral-8x7B-Holodeck-v1-i1-GGUF

Transformers
GGUF
PyTorch
English
mixtral
fine-tuned
Mixture of Experts
Inference Endpoints
Model card Files Community
1
mradermacher commited on
Commit
1a3b3d6
•
1 Parent(s): cfca466

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -42,7 +42,7 @@ more details, including on how to concatenate multi-part files.
42
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.8 | IQ3_S probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.4 | IQ3_M probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.3 | |
45
- | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 26.8 | slightly worse than Q4_K_S |
46
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_0.gguf) | i1-Q4_0 | 26.8 | fast, low quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.0 | optimal size/speed/quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.7 | fast, recommended |
@@ -50,7 +50,6 @@ more details, including on how to concatenate multi-part files.
50
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.5 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q6_K.gguf) | i1-Q6_K | 38.6 | practically like static Q6_K |
52
 
53
-
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):
56
 
 
42
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.8 | IQ3_S probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.4 | IQ3_M probably better |
44
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.3 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 26.8 | prefer IQ4_XS |
46
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_0.gguf) | i1-Q4_0 | 26.8 | fast, low quality |
47
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.0 | optimal size/speed/quality |
48
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.7 | fast, recommended |
 
50
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.5 | |
51
  | [GGUF](https://huggingface.co/mradermacher/Mixtral-8x7B-Holodeck-v1-i1-GGUF/resolve/main/Mixtral-8x7B-Holodeck-v1.i1-Q6_K.gguf) | i1-Q6_K | 38.6 | practically like static Q6_K |
52
 
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
55