Downloads · 30 days
20
18% of all-time downloads
Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill-ONNX
willopcbeta/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill-ONNX
Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill-ONNX is a text generation model from willopcbeta. Use it when you need the model to write or continue text. It is set up for transformers.js. The card lists the license as apache-2.0.
Source：TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill This model was trained on a Gemini 3 Pro Preview dataset with a high reasoning effort.
All-time downloads
109
Public
Repo size
7.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx_data2.6 GB · 36%
At a glance
- Task
- Text Generation
- Library
- transformers.js
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Feb 6, 2026
- Updated
- Feb 7, 2026
- SHA
- c3cbde47
Try a prompt
Base models
Model card
From the Hugging Face model README
Export using onnxruntime-genai:
--precision int4 --execution-provider webgpu --extra_options int4 Accuracy.level=4
--precision int4 --execution_provider cpu
Qwen3 4B Instruct 2507 - Gemini 3 Pro Preview (No Reasoning) Distill
Source：TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill
This model was trained on a Gemini 3 Pro Preview dataset with a high reasoning effort.
The reasoning summaries were then formatted out of the dataset and the model was finetuned on the final answers only.
-
🧬 Datasets:
TeichAI/gemini-3-pro-preview-high-reasoning-1000x
-
🏗 Base Model:
unsloth/Qwen3-4B-Instruct-2507
-
⚡ Use cases:
- Coding
- Science
-
∑ Stats (Dataset)
- Costs: $ 32.7 (USD)
- Total tokens (input + output): 2.73 M
This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Task
- Text Generation
- Library
- transformers.js
- Type
- qwen3
- License
- apache-2.0
- Created
- Feb 6, 2026
- Updated
- Feb 7, 2026