Downloads · 30 days
42
8% of all-time downloads
Nexus-Lumina-3B-v3
gdinexus/Nexus-Lumina-3B-v3
Nexus-Lumina-3B-v3 is a text generation model from gdinexus. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as other.
Nexus-Lumina-3B-v3 is a highly optimized, local reasoning engine fine-tuned by GDI Nexus.
All-time downloads
508
Public
Parameters
3.1B
6.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- mlx
- License
- other
- Model type
- qwen2
- Access
- Public
- Created
- Apr 17, 2026
- Updated
- Apr 18, 2026
- SHA
- 6c9b1bd9
Try a prompt
Base models
Model card
From the Hugging Face model README
Nexus-Lumina-3B-v3
Nexus-Lumina-3B-v3 is a highly optimized, local reasoning engine fine-tuned by GDI Nexus.
To bypass instruction-tuning degradation (catastrophic forgetting), we fine-tuned the raw Qwen2.5-3B base model on 17,636 rigorously filtered reasoning chains from the OpenHermes dataset. It is engineered specifically for Apple Silicon via the MLX framework, utilizing our proprietary mlx-ash-kv (Asynchronous Self-Healing KV Cache) for maximum memory stability during extended contexts.
Evaluation
Evaluated entirely locally on unified memory using the Hugging Face Leaderboard standard (25-shot):
- Benchmark: ARC-Challenge (25-shot)
- Score: 56.83% (Normalized Accuracy)
This model proves enterprise-grade 3B reasoning is achievable on local fanless hardware.
- Task
- Text Generation
- Library
- mlx
- Type
- qwen2
- License
- other
- Languages
- en
- Created
- Apr 17, 2026
- Updated
- Apr 18, 2026