6-bit Open on Hugging Face
Parameters
7.6B
Weights (est.)
≈ 6.2 GB
Mac memory (est.)
16 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/VulnLLM-R-7B-6bit --prompt "Hello"
Details
- Base model
- Virtue-AI-HUB/VulnLLM-R-7B (quantized)
- Vendor
- Virtue-AI-HUB
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- apache-2.0
- Downloads
- 58 in the last 30 days · 338 all time · 0 likes
- Published
- 2026-01-02 · updated 2026-01-02 (10mo ago)
- Languages
- en, code
- Tags
- qwen2, security, vulnerability-detection, code-analysis, reasoning
Other MLX builds of Virtue-AI-HUB/VulnLLM-R-7B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| VulnLLM-R-7B-4bit | 4-bit | ≈ 4.3 GB | 8 GB+ | 73 |
| VulnLLM-R-7B-6bit (this one) | 6-bit | ≈ 6.2 GB | 16 GB+ | 58 |
| VulnLLM-R-7B-8bit | 8-bit | ≈ 8.1 GB | 16 GB+ | 119 |