Downloads · 30 days
36
8% of all-time downloads
Qwythos-9B-v2-MLX-4bit
ahmedandaloes/Qwythos-9B-v2-MLX-4bit
Qwythos-9B-v2-MLX-4bit is a text generation model from ahmedandaloes. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
4-bit quantized MLX build of empero-ai/Qwythos-9B-v2, for fast local inference on Apple Silicon.
All-time downloads
470
Public
Parameters
9B
5.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5 GB · 100%
Parameter types
How the weights are stored.
U329B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwythos-9B-v2 — MLX 4-bit
4-bit quantized MLX build of empero-ai/Qwythos-9B-v2, for fast local inference on Apple Silicon.
- Precision: 4-bit affine, group size 64.
- Weights unchanged from source — format + precision conversion only.
- Converted with
mlx-lm.
Builds
GGUF builds: empero-ai/Qwythos-9B-v2-GGUF.
Usage
pip install mlx-lm
from mlx_lm import load, generate
model, tok = load("ahmedandaloes/Qwythos-9B-v2-MLX-4bit")
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: empero-ai/Qwythos-9B-v2. License per source (Apache-2.0 assumed; verify). MLX build for the Apple Silicon community. For authorized security work only.
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Languages
- en
- Created
- Jul 12, 2026
- Updated
- Jul 12, 2026