Downloads · 30 days
12
5% of all-time downloads
VibeThinker-3B-JANG_4M
OsaurusAI/VibeThinker-3B-JANG_4M
VibeThinker-3B-JANG_4M is a text generation model from OsaurusAI. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as mit.
All-time downloads
227
Public
Parameters
3.1B
1.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 99%
Parameter types
How the weights are stored.
U323.1B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
VibeThinker-3B · JANG_4M
Official OsaurusAI 4-bit affine (JANG_4M, group-size 64) build of WeiboAI/VibeThinker-3B (MIT) — a 3B dense reasoning model (Qwen2). Quantized by Osaurus; runs on Apple Silicon via Osaurus / mlx_lm. Emits <think> reasoning blocks.
Usage
python -m mlx_lm generate --model OsaurusAI/VibeThinker-3B-JANG_4M --prompt "What is 17 + 28?"
Or load in Osaurus.
Provenance
- Base: WeiboAI/VibeThinker-3B © Weibo AI — MIT
- Quantization: Osaurus · 4-bit affine (JANG_4M, group-size 64) · [email protected]
- Task
- Text Generation
- Library
- mlx
- Type
- qwen2
- License
- mit
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026