Total runs:
11.7K
Run Growth:
11.7K
Growth Rate:
100.00%
Sponsored by
APIMart
darkc0de / XORTRON.CriminalComputing.Q35xC46
Model's Last Updated: March 04 2026
image-text-to-text
Introduction of XORTRON.CriminalComputing.Q35xC46
Model Details of XORTRON.CriminalComputing.Q35xC46
This is a decensored version of TeichAI/Qwen3.5-27B-Claude-Opus-4.6-Distill , made using Heretic v1.2.0
Abliteration parameters
| Parameter | Value |
|---|---|
| direction_index | 51.21 |
| attn.o_proj.max_weight | 1.41 |
| attn.o_proj.max_weight_position | 41.72 |
| attn.o_proj.min_weight | 1.09 |
| attn.o_proj.min_weight_distance | 36.93 |
| mlp.down_proj.max_weight | 1.47 |
| mlp.down_proj.max_weight_position | 38.63 |
| mlp.down_proj.min_weight | 1.42 |
| mlp.down_proj.min_weight_distance | 36.17 |
Performance
| Metric | This model | Original model ( TeichAI/Qwen3.5-27B-Claude-Opus-4.6-Distill ) |
|---|---|---|
| KL divergence | 0.0079 | 0 (by definition) |
| Refusals | 21/100 | 92/100 |
Qwen3.5 27B x Claude Opus 4.6
Big thanks to @EclipseMist for providing the LoRAs for this model
Happy to share that this is one of the best models on this account for all around use (including agentic coding)
-
🧬 Datasets:
-
crownelius/Opus-4.6-Reasoning-2100x-formatted - Personal Claude Data provided by @EclipseMist
-
-
🏗 Base Model:
-
unsloth/Qwen3.5-27B
-
-
⚡ Use cases:
- Coding
- Creative Writing
- Visual Understanding
- General Purpose
Citations and Contributions
- @EclipseMist - Training and Data Curation
- @crownelius - Data Curation
- @unsloth - This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- @Qwen - Providing a fantastic, native-multimodal base model
The following best practices recommended by Qwen
Best Practices
To achieve optimal performance, we recommend the following settings:
-
Sampling Parameters :
-
We suggest using the following sets of sampling parameters depending on the mode and task type:
-
Thinking mode for general tasks
:
temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0 -
Thinking mode for precise coding tasks (e.g., WebDev)
:
temperature=0.6,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=0.0,repetition_penalty=1.0 -
Instruct (or non-thinking) mode for general tasks
:
temperature=0.7,top_p=0.8,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0 -
Instruct (or non-thinking) mode for reasoning tasks
:
temperature=1.0,top_p=1.0,top_k=40,min_p=0.0,presence_penalty=2.0,repetition_penalty=1.0
-
Thinking mode for general tasks
:
-
For supported frameworks, you can adjust the
presence_penaltyparameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
-
We suggest using the following sets of sampling parameters depending on the mode and task type:
-
Adequate Output Length : We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 81,920 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.
-
Standardize Output Format : We recommend using prompts to standardize model outputs when benchmarking.
- Math Problems : Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
-
Multiple-Choice Questions
: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the
answerfield with only the choice letter, e.g.,"answer": "C"."
-
No Thinking Content in History : In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
-
Long Video Understanding : To optimize inference efficiency for plain text and images, the
sizeparameter in the releasedvideo_preprocessor_config.jsonis conservatively configured. It is recommended to set thelongest_edgeparameter in the video_preprocessor_config file to 469,762,048 (corresponding to 224k video tokens) to enable higher frame-rate sampling for hour-scale videos and thereby achieve superior performance. For example,{"longest_edge": 469762048, "shortest_edge": 4096}Alternatively, override the default values via engine startup parameters. For implementation details, refer to: vLLM / SGLang .
Runs of darkc0de XORTRON.CriminalComputing.Q35xC46 on huggingface.co
90
Total runs
0
24-hour runs
4
3-day runs
33
7-day runs
33
30-day runs
More Information About XORTRON.CriminalComputing.Q35xC46 huggingface.co Model
Url of XORTRON.CriminalComputing.Q35xC46
XORTRON.CriminalComputing.Q35xC46 huggingface.co Url
Provider of XORTRON.CriminalComputing.Q35xC46 huggingface.co
Other API from darkc0de
Updated:September 24 2026
Total runs:
6.8K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2.7K
Run Growth:
2.7K
Growth Rate:
100.00%
Total runs:
2.0K
Run Growth:
261
Growth Rate:
13.33%
Total runs:
1.6K
Run Growth:
1.3K
Growth Rate:
80.57%
Total runs:
1.4K
Run Growth:
-4.5K
Growth Rate:
-318.31%
Total runs:
1.2K
Run Growth:
1.1K
Growth Rate:
86.16%
Total runs:
1.1K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
837
Run Growth:
90
Growth Rate:
10.75%
Total runs:
739
Run Growth:
90
Growth Rate:
12.18%
Total runs:
677
Run Growth:
54
Growth Rate:
7.98%
Total runs:
625
Run Growth:
53
Growth Rate:
8.48%
Total runs:
588
Run Growth:
75
Growth Rate:
12.76%
Total runs:
573
Run Growth:
59
Growth Rate:
10.30%
Total runs:
567
Run Growth:
0
Growth Rate:
0.00%
Total runs:
447
Run Growth:
156
Growth Rate:
34.90%
Total runs:
368
Run Growth:
171
Growth Rate:
46.47%
Total runs:
351
Run Growth:
-59
Growth Rate:
-16.81%
Total runs:
350
Run Growth:
217
Growth Rate:
62.00%
Total runs:
333
Run Growth:
333
Growth Rate:
100.00%
Total runs:
320
Run Growth:
320
Growth Rate:
100.00%
Total runs:
312
Run Growth:
68
Growth Rate:
21.79%
Total runs:
246
Run Growth:
-69
Growth Rate:
-28.05%
Total runs:
231
Run Growth:
-1.2K
Growth Rate:
-500.87%
Total runs:
226
Run Growth:
226
Growth Rate:
100.00%
Total runs:
208
Run Growth:
34
Growth Rate:
16.35%
Total runs:
207
Run Growth:
158
Growth Rate:
76.33%
Total runs:
205
Run Growth:
-1.0K
Growth Rate:
-510.24%
Total runs:
198
Run Growth:
0
Growth Rate:
0.00%
Total runs:
196
Run Growth:
149
Growth Rate:
76.02%
Total runs:
171
Run Growth:
147
Growth Rate:
85.96%
Total runs:
156
Run Growth:
-797
Growth Rate:
-510.90%
Total runs:
148
Run Growth:
53
Growth Rate:
35.81%
Total runs:
147
Run Growth:
37
Growth Rate:
25.17%
Total runs:
146
Run Growth:
-858
Growth Rate:
-587.67%
Total runs:
141
Run Growth:
11
Growth Rate:
7.80%
Total runs:
139
Run Growth:
41
Growth Rate:
29.50%
Total runs:
135
Run Growth:
54
Growth Rate:
40.00%
Total runs:
124
Run Growth:
124
Growth Rate:
100.00%
Total runs:
117
Run Growth:
-632
Growth Rate:
-540.17%
Total runs:
109
Run Growth:
1
Growth Rate:
0.92%
Total runs:
90
Run Growth:
-716
Growth Rate:
-795.56%
Total runs:
84
Run Growth:
7
Growth Rate:
8.33%
Total runs:
83
Run Growth:
4
Growth Rate:
4.82%
Total runs:
81
Run Growth:
62
Growth Rate:
76.54%
Total runs:
75
Run Growth:
24
Growth Rate:
32.00%
Total runs:
71
Run Growth:
0
Growth Rate:
0.00%
Total runs:
68
Run Growth:
-160
Growth Rate:
-235.29%
Total runs:
64
Run Growth:
-141
Growth Rate:
-220.31%
Total runs:
63
Run Growth:
8
Growth Rate:
12.70%
Total runs:
58
Run Growth:
50
Growth Rate:
86.21%
Total runs:
57
Run Growth:
52
Growth Rate:
91.23%
Total runs:
56
Run Growth:
54
Growth Rate:
96.43%
Total runs:
54
Run Growth:
46
Growth Rate:
85.19%
Total runs:
51
Run Growth:
44
Growth Rate:
86.27%
Total runs:
51
Run Growth:
46
Growth Rate:
90.20%
Total runs:
49
Run Growth:
36
Growth Rate:
73.47%
Total runs:
48
Run Growth:
25
Growth Rate:
52.08%
Total runs:
41
Run Growth:
2
Growth Rate:
4.88%
Total runs:
40
Run Growth:
1
Growth Rate:
2.50%
Total runs:
38
Run Growth:
6
Growth Rate:
15.79%
Total runs:
37
Run Growth:
8
Growth Rate:
21.62%
Total runs:
35
Run Growth:
23
Growth Rate:
65.71%
Total runs:
35
Run Growth:
2
Growth Rate:
5.71%
Total runs:
33
Run Growth:
33
Growth Rate:
100.00%
Total runs:
27
Run Growth:
0
Growth Rate:
0.00%
Total runs:
26
Run Growth:
4
Growth Rate:
15.38%
Total runs:
25
Run Growth:
13
Growth Rate:
52.00%
Total runs:
23
Run Growth:
0
Growth Rate:
0.00%
Total runs:
23
Run Growth:
23
Growth Rate:
100.00%
Total runs:
18
Run Growth:
14
Growth Rate:
77.78%
Total runs:
18
Run Growth:
-34
Growth Rate:
-188.89%
Total runs:
18
Run Growth:
6
Growth Rate:
33.33%
Total runs:
14
Run Growth:
14
Growth Rate:
100.00%
Total runs:
10
Run Growth:
-3
Growth Rate:
-30.00%
Total runs:
9
Run Growth:
0
Growth Rate:
0.00%
Total runs:
8
Run Growth:
0
Growth Rate:
0.00%
Total runs:
8
Run Growth:
0
Growth Rate:
0.00%
Total runs:
8
Run Growth:
0
Growth Rate:
0.00%
Total runs:
7
Run Growth:
0
Growth Rate:
0.00%
Total runs:
7
Run Growth:
7
Growth Rate:
100.00%
Total runs:
6
Run Growth:
1
Growth Rate:
16.67%
Total runs:
6
Run Growth:
-11
Growth Rate:
-183.33%