Hugging Face's logo

mradermacher
/
Breeze-7B-Instruct-v0_1-GGUF

Transformers
GGUF
Chinese
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
a51fa8d
·
verified ·
1 Parent(s): a1d58b8

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -30,7 +30,18 @@ more details, including on how to concatenate multi-part files.
30
 
31
  | Link | Type | Size/GB | Notes |
32
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
33
  | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
 
 
 
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.f16.gguf) | f16 | 15.1 | 16 bpw, overkill |
35
 
36
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
30
 
31
  | Link | Type | Size/GB | Notes |
32
  |:-----|:-----|--------:|:------|
33
+ | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q2_K.gguf) | Q2_K | 3.0 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
36
+ | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.4 | fast on arm, low quality |
39
  | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
40
+ | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
41
+ | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.Q8_0.gguf) | Q8_0 | 8.1 | fast, best quality |
45
  | [GGUF](https://huggingface.co/mradermacher/Breeze-7B-Instruct-v0_1-GGUF/resolve/main/Breeze-7B-Instruct-v0_1.f16.gguf) | f16 | 15.1 | 16 bpw, overkill |
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant