Hugging Face's logo

mradermacher
/
blossom-v4-baichuan2-7b-GGUF

Transformers
GGUF
Chinese
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
b58daf1
•
1 Parent(s): 60b7549

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -36,7 +36,18 @@ more details, including on how to concatenate multi-part files.
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
38
  | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q2_K.gguf) | Q2_K | 3.1 | |
 
 
 
 
 
39
  | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q4_K_S.gguf) | Q4_K_S | 4.5 | fast, recommended |
 
 
 
 
 
 
40
 
41
  Here is a handy graph by ikawrakow comparing some lower-quality quant
42
  types (lower is better):
 
36
  | Link | Type | Size/GB | Notes |
37
  |:-----|:-----|--------:|:------|
38
  | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q2_K.gguf) | Q2_K | 3.1 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q3_K_S.gguf) | Q3_K_S | 3.5 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
41
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.IQ4_XS.gguf) | IQ4_XS | 4.3 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.5 | fast on arm, low quality |
44
  | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q4_K_S.gguf) | Q4_K_S | 4.5 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q4_K_M.gguf) | Q4_K_M | 4.7 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q6_K.gguf) | Q6_K | 6.3 | very good quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.Q8_0.gguf) | Q8_0 | 8.1 | fast, best quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/blossom-v4-baichuan2-7b-GGUF/resolve/main/blossom-v4-baichuan2-7b.f16.gguf) | f16 | 15.1 | 16 bpw, overkill |
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):