Text Generation
MLX
Safetensors
English
Chinese
gemma4_unified
gemma4
humanizer
text-rewriting
unofficial-conversion
8-bit precision
Instructions to use npario/humanizer-12b-mlx-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use npario/humanizer-12b-mlx-8bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("npario/humanizer-12b-mlx-8bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use npario/humanizer-12b-mlx-8bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "npario/humanizer-12b-mlx-8bit" --prompt "Once upon a time"
- Atomic Chat
Download CONVERTED.json from npario/humanizer-12b-mlx-8bit: direct link, hf CLI and curl.
- Browser
- Download file 242 Bytes
-
https://huggingface.co/npario/humanizer-12b-mlx-8bit/resolve/main/CONVERTED.json
- Command line
-
hf download hf://npario/humanizer-12b-mlx-8bit/CONVERTED.json
-
curl -L -o CONVERTED.json https://huggingface.co/npario/humanizer-12b-mlx-8bit/resolve/main/CONVERTED.json
242 Bytes
| { | |
| "completed_at": "2026-10-09T01:02:49.426999+00:00", | |
| "conversion_seconds": 96.77952861200004, | |
| "identity": "134a98b195bd0c11a340ce173b5e3a77069ae01017975ab401746008b6f0fc3a", | |
| "status": "conversion_complete_audit_record_is_separate" | |
| } | |