Downloads · 30 days
45
9% of all-time downloads
nightmedia/Gemma-3-27b-it-HERETIC-Gemini-1000x-Deep-Reasoning-q6-mlx
Gemma-3-27b-it-HERETIC-Gemini-1000x-Deep-Reasoning-q6-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.
Downloads · 30 days
45
9% of all-time downloads
All-time downloads
513
Public
Parameters
27B
22 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors21.9 GB · 100%
How the weights are stored.
U3227B · 100%
From the Hugging Face model README
Quantized model performance
q6 0.599,0.757,0.876,0.770,0.466,0.806,0.756
Brainwaves for regular vs 1000x models in the q6 quant
regular 0.594,0.746,0.881,0.779,0.464,0.816,0.751
1000x 0.599,0.757,0.876,0.770,0.466,0.806,0.756
Heretic ablation improved the model arc/arc_easy significantly, with minor drops in other places
-G
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Gemma-3-27b-it-HERETIC-Gemini-1000x-Deep-Reasoning-q6-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,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)