Modelpublic

aimeri/spoomplesmaxx-thrasher-24B-mlx-6bit

sourceHugging Faceapache-2.0updated 29d agoView on Hugging Face

0likes185downloads

Model Card

spoomplesmaxx-thrasher-24B — MLX 6-bit

6-bit MLX quant of spoomplesmaxx-thrasher-24B ("Thrash Metal", mimids 02) for Apple Silicon. ~18 GB — the quality pick for 32GB+ Macs. ChatML template embedded in both tokenizer_config.json and chat_template.jinja.

bash

pip install mlx-lm
mlx_lm.chat --model aimeri/spoomplesmaxx-thrasher-24B-mlx-6bit

Sampler (swept on the full-precision model): temperature 1.0 · min_p 0.05. A mild repetition_penalty 1.05 eliminated the verbatim-loop tail in our sweep at the cost of a rare unfinished turn — a reasonable opt-in. Tighter on memory? The 4-bit (~13 GB) fits a 24GB Mac comfortably. See the main card for the full story.

For adults. Stays in character by design; bring your own moderation. Apache 2.0.