Hugging Face's logo

mradermacher
/
Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF

Transformers
GGUF
English
text-generation-inference
abliterated
v1.0
conversational
Model card Files
xet
Community
mradermacher commited on
Commit
07da256
·
verified ·
1 Parent(s): a81cd7a

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -43,6 +43,13 @@ more details, including on how to concatenate multi-part files.
43
  |:-----|:-----|--------:|:------|
44
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF/resolve/main/Qwen3-VL-30B-A3B-Instruct-abliterated-v1.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.8 | multi-modal supplement |
45
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF/resolve/main/Qwen3-VL-30B-A3B-Instruct-abliterated-v1.mmproj-f16.gguf) | mmproj-f16 | 1.2 | multi-modal supplement |
 
 
 
 
 
 
 
46
 
47
  Here is a handy graph by ikawrakow comparing some lower-quality quant
48
  types (lower is better):
 
43
  |:-----|:-----|--------:|:------|
44
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF/resolve/main/Qwen3-VL-30B-A3B-Instruct-abliterated-v1.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.8 | multi-modal supplement |
45
  | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF/resolve/main/Qwen3-VL-30B-A3B-Instruct-abliterated-v1.mmproj-f16.gguf) | mmproj-f16 | 1.2 | multi-modal supplement |
46
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF/resolve/main/Qwen3-VL-30B-A3B-Instruct-abliterated-v1.Q2_K.gguf) | Q2_K | 11.4 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF/resolve/main/Qwen3-VL-30B-A3B-Instruct-abliterated-v1.Q3_K_S.gguf) | Q3_K_S | 13.4 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF/resolve/main/Qwen3-VL-30B-A3B-Instruct-abliterated-v1.Q3_K_M.gguf) | Q3_K_M | 14.8 | lower quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF/resolve/main/Qwen3-VL-30B-A3B-Instruct-abliterated-v1.Q3_K_L.gguf) | Q3_K_L | 16.0 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF/resolve/main/Qwen3-VL-30B-A3B-Instruct-abliterated-v1.Q4_K_S.gguf) | Q4_K_S | 17.6 | fast, recommended |
51
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF/resolve/main/Qwen3-VL-30B-A3B-Instruct-abliterated-v1.Q6_K.gguf) | Q6_K | 25.2 | very good quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-30B-A3B-Instruct-abliterated-v1-GGUF/resolve/main/Qwen3-VL-30B-A3B-Instruct-abliterated-v1.Q8_0.gguf) | Q8_0 | 32.6 | fast, best quality |
53
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):