Hugging Face's logo

VECTORVV1
/
GLM-4.7-Flash

Image-Text-to-Text
GGUF
English
Chinese
multilingual
uncensored
qwen3.5
Mixture of Experts
vision
multimodal
imatrix
conversational
Model card Files
xet
 Community
VECTORVV1 HauhauCS commited on
Commit
e39c917
·
0 Parent(s):

Duplicate from HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive

Browse files
Files changed (3) hide show
  1. .gitattributes +49 -0
  2. Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf +3 -0
  3. README.md +111 -0
.gitattributes ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ mmproj-Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-f16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf filter=lfs diff=lfs merge=lfs -text
Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d6052c022e478548370d5a3d82539437d118b8b90b990ab960f1aed6376ef0
3
+ size 78682967648
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - uncensored
5
+ - qwen3.5
6
+ - moe
7
+ - gguf
8
+ - vision
9
+ - multimodal
10
+ language:
11
+ - en
12
+ - zh
13
+ - multilingual
14
+ pipeline_tag: image-text-to-text
15
+ base_model: Qwen/Qwen3.5-122B-A10B
16
+ ---
17
+
18
+ # Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive
19
+
20
+ > **[Join the Discord](https://discord.gg/SZ5vacTXYf)** for updates, roadmaps, projects, or just to chat.
21
+
22
+ Qwen3.5-122B-A10B uncensored by HauhauCS. **0/465 refusals.**
23
+
24
+ ## About
25
+
26
+ No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals.
27
+
28
+ These are meant to be the best lossless uncensored models out there.
29
+
30
+ ## Aggressive Variant
31
+
32
+ Stronger uncensoring — model is fully unlocked and won't refuse prompts. Disclaimers that were present in previous releases have been significantly reduced in this version.
33
+
34
+ For a more conservative uncensor that keeps some safety guardrails, check the Balanced variant when it's available.
35
+
36
+ ## What are K_P quants?
37
+
38
+ K_P ("Perfect") quants are HauhauCS custom quantizations that use model-specific analysis to selectively preserve quality where it matters most. Each model gets its own optimized quantization profile.
39
+
40
+ A K_P quant effectively bumps quality up by 1-2 quant levels at only ~5-15% larger file size than the base quant. Fully compatible with llama.cpp, LM Studio, and any GGUF-compatible runtime — no special builds needed.
41
+
42
+ ## Downloads
43
+
44
+ | File | Quant | Size |
45
+ |------|-------|------|
46
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf | Q8_K_P | 145 GB |
47
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf | Q6_K_P | 105 GB |
48
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf | Q6_K | 100 GB |
49
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf | Q5_K_P | 94 GB |
50
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q5_K_M.gguf | Q5_K_M | 87 GB |
51
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf | Q4_K_P | 79 GB |
52
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf | Q4_K_M | 74 GB |
53
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf | IQ4_XS | 65 GB |
54
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf | Q3_K_P | 63 GB |
55
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q3_K_M.gguf | Q3_K_M | 59 GB |
56
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf | IQ3_M | 54 GB |
57
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ3_XXS.gguf | IQ3_XXS | 47 GB |
58
+ | Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ2_M.gguf | IQ2_M | 40 GB |
59
+ | mmproj-Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-f16.gguf | mmproj (f16) | 867 MB |
60
+
61
+ **Note:** K_P quants may show as "?" in LM Studio's quant column. This is a display issue only — the model loads and runs fine.
62
+
63
+ ## Specs
64
+
65
+ - 122B total parameters, ~10B active per forward pass (MoE)
66
+ - 256 experts, 8 routed + 1 shared per token
67
+ - Hybrid architecture: Gated DeltaNet linear attention + full softmax attention (3:1 ratio)
68
+ - 48 layers, pattern: 12 x (3 x DeltaNet-MoE + 1 x Attention-MoE)
69
+ - 262K native context
70
+ - Natively multimodal (text, image, video)
71
+ - 248K vocabulary, 201 languages
72
+ - Based on [Qwen/Qwen3.5-122B-A10B](https://huggingface.co/Qwen/Qwen3.5-122B-A10B)
73
+
74
+ ## Recommended Settings
75
+
76
+ From the official Qwen authors:
77
+
78
+ **Thinking mode (default):**
79
+ - General: `temperature=1.0, top_p=0.95, top_k=20, min_p=0, presence_penalty=1.5`
80
+ - Coding/precise tasks: `temperature=0.6, top_p=0.95, top_k=20, min_p=0, presence_penalty=0`
81
+
82
+ **Non-thinking mode:**
83
+ - General: `temperature=0.7, top_p=0.8, top_k=20, min_p=0, presence_penalty=1.5`
84
+ - Reasoning tasks: `temperature=1.0, top_p=1.0, top_k=40, min_p=0, presence_penalty=2.0`
85
+
86
+ **Important:**
87
+ - Use `--jinja` flag with llama.cpp for proper chat template handling
88
+ - Thinking mode is on by default — to disable, use `--chat-template-kwargs '{"enable_thinking":false}'` or edit the jinja template
89
+ - Vision support requires the `mmproj` file alongside the main GGUF
90
+
91
+ ## Usage
92
+
93
+ Works with llama.cpp, LM Studio, Jan, koboldcpp, and other GGUF-compatible runtimes.
94
+
95
+ ```bash
96
+ # Text only
97
+ llama-cli -m Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
98
+ --jinja -c 131072 -ngl 99
99
+
100
+ # With vision
101
+ llama-cli -m Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
102
+ --mmproj mmproj-Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-f16.gguf \
103
+ --jinja -c 131072 -ngl 99
104
+ ```
105
+
106
+ ## Other Models
107
+
108
+ - [Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive](https://huggingface.co/HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive)
109
+ - [Qwen3.5-27B-Uncensored-HauhauCS-Aggressive](https://huggingface.co/HauhauCS/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive)
110
+ - [Qwen3.5-9B-Uncensored-HauhauCS-Aggressive](https://huggingface.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive)
111
+ - [Qwen3.5-4B-Uncensored-HauhauCS-Aggressive](https://huggingface.co/HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive)