Hugging Face's logo

mradermacher
/
Beyonder-4x7B-v2-i1-GGUF

Transformers
GGUF
English
Mixture of Experts
Merge
mergekit
Mistral
openchat/openchat-3.5-1210
beowolx/CodeNinja-1.0-OpenChat-7B
maywell/PiVoT-0.1-Starling-LM-RP
WizardLM/WizardMath-7B-V1.1
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
59fa5c6
•
1 Parent(s): 4ee9cdc

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -22,9 +22,12 @@ more details, including on how to concatenate multi-part files.
22
  | Link | Type | Size/GB | Notes |
23
  |:-----|:-----|--------:|:------|
24
  | [GGUF](https://huggingface.co/mradermacher/Beyonder-4x7B-v2-i1-GGUF/resolve/main/Beyonder-4x7B-v2.i1-Q2_K.gguf) | i1-Q2_K | 9.1 | IQ3_XXS probably better |
 
25
  | [GGUF](https://huggingface.co/mradermacher/Beyonder-4x7B-v2-i1-GGUF/resolve/main/Beyonder-4x7B-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.8 | IQ3_S probably better |
 
26
  | [GGUF](https://huggingface.co/mradermacher/Beyonder-4x7B-v2-i1-GGUF/resolve/main/Beyonder-4x7B-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.0 | optimal size/speed/quality |
27
  | [GGUF](https://huggingface.co/mradermacher/Beyonder-4x7B-v2-i1-GGUF/resolve/main/Beyonder-4x7B-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.9 | fast, medium quality |
 
28
 
29
 
30
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
22
  | Link | Type | Size/GB | Notes |
23
  |:-----|:-----|--------:|:------|
24
  | [GGUF](https://huggingface.co/mradermacher/Beyonder-4x7B-v2-i1-GGUF/resolve/main/Beyonder-4x7B-v2.i1-Q2_K.gguf) | i1-Q2_K | 9.1 | IQ3_XXS probably better |
25
+ | [GGUF](https://huggingface.co/mradermacher/Beyonder-4x7B-v2-i1-GGUF/resolve/main/Beyonder-4x7B-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.7 | IQ3_XS probably better |
26
  | [GGUF](https://huggingface.co/mradermacher/Beyonder-4x7B-v2-i1-GGUF/resolve/main/Beyonder-4x7B-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 11.8 | IQ3_S probably better |
27
+ | [GGUF](https://huggingface.co/mradermacher/Beyonder-4x7B-v2-i1-GGUF/resolve/main/Beyonder-4x7B-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 12.8 | IQ3_M probably better |
28
  | [GGUF](https://huggingface.co/mradermacher/Beyonder-4x7B-v2-i1-GGUF/resolve/main/Beyonder-4x7B-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.0 | optimal size/speed/quality |
29
  | [GGUF](https://huggingface.co/mradermacher/Beyonder-4x7B-v2-i1-GGUF/resolve/main/Beyonder-4x7B-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 14.9 | fast, medium quality |
30
+ | [GGUF](https://huggingface.co/mradermacher/Beyonder-4x7B-v2-i1-GGUF/resolve/main/Beyonder-4x7B-v2.i1-Q6_K.gguf) | i1-Q6_K | 20.1 | practically like static Q6_K |
31
 
32
 
33
  Here is a handy graph by ikawrakow comparing some lower-quality quant