security-llama3.2-3b — MLX 8-bit

8-bit quantized MLX build of viettelsecurity-ai/security-llama3.2-3b, for fast local inference on Apple Silicon.

• Precision: 8-bit affine, group size 64.
• Weights unchanged from source — format + precision conversion only.
• Converted with mlx-lm.

Builds

GGUF builds: prithivMLmods/Security-Llama3.2-3B-GGUF.

Usage

pip install mlx-lm

from mlx_lm import load, generate
model, tok = load("ahmedandaloes/security-llama3.2-3b-MLX-8bit")
p = tok.apply_chat_template([{"role":"user","content":"Name a common web vulnerability."}], add_generation_prompt=True)
print(generate(model, tok, prompt=p, max_tokens=200, verbose=True))

Attribution

Source: viettelsecurity-ai/security-llama3.2-3b. License per source (Apache-2.0 assumed; verify). MLX build for the Apple Silicon community. For authorized security work only.