Hugging Face's logo

mradermacher
/
CabraQwen7b-i1-GGUF

Transformers
GGUF
Portuguese
English
text-generation-inference
qwen
brazil
brasil
portuguese
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
0005a8c
·
verified ·
1 Parent(s): bbd91b1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -47,15 +47,20 @@ more details, including on how to concatenate multi-part files.
47
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
48
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q2_K.gguf) | i1-Q2_K | 3.2 | IQ3_XXS probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality |
 
 
50
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.7 | IQ3_XS probably better |
51
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.8 | |
52
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.0 | IQ3_S probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.3 | IQ3_M probably better |
54
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.4 | |
55
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.6 | prefer IQ4_XS |
 
56
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
57
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.9 | fast, recommended |
 
58
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.5 | |
 
59
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K |
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
47
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
48
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q2_K.gguf) | i1-Q2_K | 3.2 | IQ3_XXS probably better |
49
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.5 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ3_S.gguf) | i1-IQ3_S | 3.7 | beats Q3_K* |
52
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.7 | IQ3_XS probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.8 | |
54
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.0 | IQ3_S probably better |
55
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.3 | IQ3_M probably better |
56
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.4 | |
57
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.6 | prefer IQ4_XS |
58
+ | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q4_0.gguf) | i1-Q4_0 | 4.6 | fast, low quality |
59
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
60
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.9 | fast, recommended |
61
+ | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q4_1.gguf) | i1-Q4_1 | 5.1 | |
62
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.5 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.6 | |
64
  | [GGUF](https://huggingface.co/mradermacher/CabraQwen7b-i1-GGUF/resolve/main/CabraQwen7b.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K |
65
 
66
  Here is a handy graph by ikawrakow comparing some lower-quality quant