Transformers
GGUF
llama
TheBloke commited on
Commit
2afc466
1 Parent(s): d3e1e3a

Initial GGUF model commit

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -100,14 +100,14 @@ Refer to the Provided Files table below to see what files use which methods, and
100
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
101
  | ---- | ---- | ---- | ---- | ---- | ----- |
102
  | [puddlejumper-13b.q2_K.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q2_K.gguf) | q2_K | 2 | 5.66 GB| 8.16 GB | smallest, significant quality loss - not recommended for most purposes |
103
- | [puddlejumper-13b.q3_K_L.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q3_K_L.gguf) | q3_K_L | 3 | 7.14 GB| 9.64 GB | small, substantial quality loss |
104
- | [puddlejumper-13b.q3_K_M.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q3_K_M.gguf) | q3_K_M | 3 | 6.55 GB| 9.05 GB | very small, high quality loss |
105
  | [puddlejumper-13b.q3_K_S.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q3_K_S.gguf) | q3_K_S | 3 | 5.87 GB| 8.37 GB | very small, high quality loss |
106
- | [puddlejumper-13b.q4_K_M.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q4_K_M.gguf) | q4_K_M | 4 | 8.06 GB| 10.56 GB | medium, balanced quality - recommended |
 
107
  | [puddlejumper-13b.q4_K_S.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q4_K_S.gguf) | q4_K_S | 4 | 7.61 GB| 10.11 GB | small, greater quality loss |
 
108
  | [puddlejumper-13b.q5_0.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q5_0.gguf) | q5_0 | 5 | 8.95 GB| 11.45 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
109
- | [puddlejumper-13b.q5_K_M.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q5_K_M.gguf) | q5_K_M | 5 | 9.40 GB| 11.90 GB | large, very low quality loss - recommended |
110
  | [puddlejumper-13b.q5_K_S.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q5_K_S.gguf) | q5_K_S | 5 | 9.15 GB| 11.65 GB | large, low quality loss - recommended |
 
111
  | [puddlejumper-13b.q6_K.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q6_K.gguf) | q6_K | 6 | 10.83 GB| 13.33 GB | very large, extremely low quality loss |
112
  | [puddlejumper-13b.q8_0.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q8_0.gguf) | q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
113
 
 
100
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
101
  | ---- | ---- | ---- | ---- | ---- | ----- |
102
  | [puddlejumper-13b.q2_K.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q2_K.gguf) | q2_K | 2 | 5.66 GB| 8.16 GB | smallest, significant quality loss - not recommended for most purposes |
 
 
103
  | [puddlejumper-13b.q3_K_S.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q3_K_S.gguf) | q3_K_S | 3 | 5.87 GB| 8.37 GB | very small, high quality loss |
104
+ | [puddlejumper-13b.q3_K_M.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q3_K_M.gguf) | q3_K_M | 3 | 6.55 GB| 9.05 GB | very small, high quality loss |
105
+ | [puddlejumper-13b.q3_K_L.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q3_K_L.gguf) | q3_K_L | 3 | 7.14 GB| 9.64 GB | small, substantial quality loss |
106
  | [puddlejumper-13b.q4_K_S.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q4_K_S.gguf) | q4_K_S | 4 | 7.61 GB| 10.11 GB | small, greater quality loss |
107
+ | [puddlejumper-13b.q4_K_M.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q4_K_M.gguf) | q4_K_M | 4 | 8.06 GB| 10.56 GB | medium, balanced quality - recommended |
108
  | [puddlejumper-13b.q5_0.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q5_0.gguf) | q5_0 | 5 | 8.95 GB| 11.45 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
 
109
  | [puddlejumper-13b.q5_K_S.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q5_K_S.gguf) | q5_K_S | 5 | 9.15 GB| 11.65 GB | large, low quality loss - recommended |
110
+ | [puddlejumper-13b.q5_K_M.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q5_K_M.gguf) | q5_K_M | 5 | 9.40 GB| 11.90 GB | large, very low quality loss - recommended |
111
  | [puddlejumper-13b.q6_K.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q6_K.gguf) | q6_K | 6 | 10.83 GB| 13.33 GB | very large, extremely low quality loss |
112
  | [puddlejumper-13b.q8_0.gguf](https://huggingface.co/TheBloke/PuddleJumper-13B-GGUF/blob/main/puddlejumper-13b.q8_0.gguf) | q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |
113