Hugging Face's logo
Gheorghe Chesler's picture
In a Training Loop 🔄
113 3 39

Gheorghe Chesler PRO

nightmedia
Grok27's profile picture benpaodexiniu's profile picture wuwuwuzz's profile picture
·

AI & ML interests

Nightmedia: human-Like AI and the MLX Deckard(qx) Formula Donations are appreciated: BTC:36d7U1n3MFaXgnNRAaEL3Pa3Hy6oFhM7XY

Recent Activity

replied to their post about 7 hours ago
The Qwen3.5-27B performance landscape I started gathering some numbers on the 27Bs. You might have noticed that reported metrics differ from Thinking to Instruct models and this is expected. The mxfp8/mxfp4 are the most stable quants I could measure, and I provided Deckard(qx) quants where possible Converting a Thinking model to Instruct The model is thinking/instruct, and the instruct mode can be forced by setting the first line of the jinja template to ``` {%- set enable_thinking = false %} ``` Qwen3.5-27B-Text This is a model I tested where the vision tower was removed, its performance is the same as the VL model. https://huggingface.co/nightmedia/Qwen3.5-27B-Text-qx86-hi-mlx ``` quant arc arc/e boolq hswag obkqa piqa wino qx86-hi 0.443,0.498,0.857,0.701,0.372,0.770,0.752 mxfp4 0.460,0.527,0.871,0.694,0.370,0.772,0.752 ``` DavidAU/Qwen3.5-27B-Claude-4.6-OS-INSTRUCT On the top of the heap of the models I tested, as far as metrics go, is this model created by DavidAU. Samples of the output are provided on the model card. https://huggingface.co/nightmedia/Qwen3.5-27B-Claude-4.6-OS-INSTRUCT-mxfp8-mlx ``` quant arc arc/e boolq hswag obkqa piqa wino mxfp8 0.675,0.827,0.900,0.750,0.496,0.800,0.721 qx86-hi 0.667,0.824,0.902,0.752,0.502,0.791,0.725 qx64-hi 0.664,0.820,0.902 mxfp4 0.653,0.815,0.899 ``` For the Thinking version, see https://huggingface.co/nightmedia/Qwen3.5-27B-Architect-Claude-qx86-hi-mlx More metrics in comments. -G P.S. I will update this as soon as I have new numbers or I found a typo--whichever comes first. The models that show just the arc-check numbers are in the test queue and will be updated soon.
updated a model about 8 hours ago
nightmedia/Qwen3.5-27B-Engineer-Deckard-Gemini-qx86-hi-mlx
liked a model about 8 hours ago
DavidAU/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking
View all activity

Organizations

Nightmedia AI's profile picture