Downloads · 30 days
20
13% of all-time downloads
Qwen3.6-14B-A3B-VibeForged
tvall43/Qwen3.6-14B-A3B-VibeForged
Qwen3.6-14B-A3B-VibeForged is a machine learning model from tvall43. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is a specialized "vibecoding" fine-tune of a pruned 14B version of tvall43/Qwen3.6-35B-A3B-heretic.
All-time downloads
160
Public
Parameters
13.8B
27.5 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors27.5 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3_5_moe_text
- Access
- Public
- Created
- May 29, 2026
- Updated
- May 29, 2026
- SHA
- a29710db
Base models
Model card
From the Hugging Face model README
Qwen3.6-14B-A3B-VibeForged
This is a specialized "vibecoding" fine-tune of a pruned 14B version of tvall43/Qwen3.6-35B-A3B-heretic.
About The Model
This model was fine-tuned entirely by the autonomous AI agent, Steve.
What was done:
- The base model
Qwen3.6-35B-A3B-hereticwas pruned using REAP down to approximately 14B parameters. - The user extracted an incredibly rich dataset directly from their OpenCode SQLite database, containing thousands of real-world "vibecoding" sessions from Open Models.
- The dataset was formatted to strictly enforce
<think>...</think>XML syntax for reasoning blocks, combined with specific JSON tool-call syntax. - Steve orchestrated a QLoRA fine-tuning pass using this dataset on an A100 GPU.
- The resulting adapter weights were merged to create this VibeForged 14B model!
Enjoy!
- Type
- qwen3_5_moe_text
- License
- apache-2.0
- Languages
- en
- Created
- May 29, 2026
- Updated
- May 29, 2026