Hugging Face's logo

tensorblock
/
sn29_v31-GGUF

Transformers
GGUF
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
1be7806
•
1 Parent(s): a372775

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -43,18 +43,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
43
 
44
  | Filename | Quant type | File Size | Description |
45
  | -------- | ---------- | --------- | ----------- |
46
- | [sn29_v31-Q2_K.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q2_K.gguf) | Q2_K | 2.067 GB | smallest, significant quality loss - not recommended for most purposes |
47
- | [sn29_v31-Q3_K_S.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q3_K_S.gguf) | Q3_K_S | 2.461 GB | very small, high quality loss |
48
- | [sn29_v31-Q3_K_M.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q3_K_M.gguf) | Q3_K_M | 2.871 GB | very small, high quality loss |
49
- | [sn29_v31-Q3_K_L.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q3_K_L.gguf) | Q3_K_L | 3.069 GB | small, substantial quality loss |
50
- | [sn29_v31-Q4_0.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q4_0.gguf) | Q4_0 | 3.196 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
51
- | [sn29_v31-Q4_K_S.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q4_K_S.gguf) | Q4_K_S | 3.215 GB | small, greater quality loss |
52
- | [sn29_v31-Q4_K_M.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q4_K_M.gguf) | Q4_K_M | 3.521 GB | medium, balanced quality - recommended |
53
- | [sn29_v31-Q5_0.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q5_0.gguf) | Q5_0 | 3.888 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
54
- | [sn29_v31-Q5_K_S.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q5_K_S.gguf) | Q5_K_S | 3.888 GB | large, low quality loss - recommended |
55
- | [sn29_v31-Q5_K_M.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q5_K_M.gguf) | Q5_K_M | 4.148 GB | large, very low quality loss - recommended |
56
- | [sn29_v31-Q6_K.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q6_K.gguf) | Q6_K | 4.623 GB | very large, extremely low quality loss |
57
- | [sn29_v31-Q8_0.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q8_0.gguf) | Q8_0 | 5.987 GB | very large, extremely low quality loss - not recommended |
58
 
59
 
60
  ## Downloading instruction
 
43
 
44
  | Filename | Quant type | File Size | Description |
45
  | -------- | ---------- | --------- | ----------- |
46
+ | [sn29_v31-Q2_K.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q2_K.gguf) | Q2_K | 1.925 GB | smallest, significant quality loss - not recommended for most purposes |
47
+ | [sn29_v31-Q3_K_S.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q3_K_S.gguf) | Q3_K_S | 2.292 GB | very small, high quality loss |
48
+ | [sn29_v31-Q3_K_M.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q3_K_M.gguf) | Q3_K_M | 2.674 GB | very small, high quality loss |
49
+ | [sn29_v31-Q3_K_L.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q3_K_L.gguf) | Q3_K_L | 2.859 GB | small, substantial quality loss |
50
+ | [sn29_v31-Q4_0.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q4_0.gguf) | Q4_0 | 2.976 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
51
+ | [sn29_v31-Q4_K_S.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q4_K_S.gguf) | Q4_K_S | 2.994 GB | small, greater quality loss |
52
+ | [sn29_v31-Q4_K_M.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q4_K_M.gguf) | Q4_K_M | 3.280 GB | medium, balanced quality - recommended |
53
+ | [sn29_v31-Q5_0.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q5_0.gguf) | Q5_0 | 3.621 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
54
+ | [sn29_v31-Q5_K_S.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q5_K_S.gguf) | Q5_K_S | 3.621 GB | large, low quality loss - recommended |
55
+ | [sn29_v31-Q5_K_M.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q5_K_M.gguf) | Q5_K_M | 3.863 GB | large, very low quality loss - recommended |
56
+ | [sn29_v31-Q6_K.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q6_K.gguf) | Q6_K | 4.305 GB | very large, extremely low quality loss |
57
+ | [sn29_v31-Q8_0.gguf](https://huggingface.co/tensorblock/sn29_v31-GGUF/blob/main/sn29_v31-Q8_0.gguf) | Q8_0 | 5.576 GB | very large, extremely low quality loss - not recommended |
58
 
59
 
60
  ## Downloading instruction