Downloads · 30 days
6.2K
26% of all-time downloads
nightmedia/OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4-q8-hi-mlx
OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4-q8-hi-mlx is a text generation model from nightmedia. 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.
Downloads · 30 days
6.2K
26% of all-time downloads
All-time downloads
24.3K
Public
Parameters
20.9B
12.2 GB on disk
Likes
8
Public
Click a slice to open those files.
.safetensors12.2 GB · 100%
How the weights are stored.
U3220.9B · 100%
From the Hugging Face model README
Perplexity: 5.920 ± 0.050
Evaluation time: 154.99 seconds
Peak memory: 17.93 GB
Tokens per second: 844
Detailed metrics coming soon.
-G
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4-q8-hi-mlx")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4
response = generate(model, tokenizer, prompt=prompt, verbose=True)