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
3dfc56f
·
verified ·
1 Parent(s): 1fd3930

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -35,8 +35,12 @@ more details, including on how to concatenate multi-part files.
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
 
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.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q3_K_S.gguf.part2of2) | Q3_K_S | 52.9 | |
39
  | [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* |
40
+ | [PART 1](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.IQ3_M.gguf.part2of2) | IQ3_M | 55.4 | |
41
+ | [PART 1](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q3_K_M.gguf.part2of2) | Q3_K_M | 59.2 | lower quality |
42
  | [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 |
43
+ | [PART 1](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/lumikabra-123B_v0.4-GGUF/resolve/main/lumikabra-123B_v0.4.Q6_K.gguf.part3of3) | Q6_K | 100.7 | very good quality |
44
  | [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 |
45
 
46
  Here is a handy graph by ikawrakow comparing some lower-quality quant