Hugging Face's logo

mradermacher
/
lumikabra-123B_v0.4-GGUF

Transformers
GGUF
English
mergekit
lumikabra-123B
Inference Endpoints
conversational
Model card Files Community
1
mradermacher commited on
Commit
dbff669
·
verified ·
1 Parent(s): 6f704b1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -34,7 +34,10 @@ more details, including on how to concatenate multi-part files.
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
 
37
  | [PART 1](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.IQ3_S.gguf.part2of2) | IQ3_S | 53.1 | beats Q3_K* |
 
 
38
 
39
  Here is a handy graph by ikawrakow comparing some lower-quality quant
40
  types (lower is better):
 
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
+ | [GGUF](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q2_K.gguf) | Q2_K | 45.3 | |
38
  | [PART 1](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.IQ3_S.gguf.part2of2) | IQ3_S | 53.1 | beats Q3_K* |
39
+ | [PART 1](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q4_K_S.gguf.part2of2) | Q4_K_S | 69.7 | fast, recommended |
40
+ | [PART 1](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q8_0.gguf.part3of3) | Q8_0 | 130.4 | fast, best quality |
41
 
42
  Here is a handy graph by ikawrakow comparing some lower-quality quant
43
  types (lower is better):