🏗️ Building on HF

Philip John Basile PRO

philipjohnbasile

·

https://huggingface.co/spaces/philipjohnbasile/local-ai-guide

AI & ML interests

Open-source AI engineer building for Apple Silicon. Contributor to Apple's MLX and MLX-LM, with merged fixes for Metal kernels and model conversion. Creator of Wisp Coder. Sharing MLX models, training data, interactive demos, and reproducible research.

Recent Activity

published a model 9 days ago

philipjohnbasile/DavidAU-Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-MTPLX

liked a model 16 days ago

philipjohnbasile/wisp-coder-110m

updated a model 16 days ago

philipjohnbasile/wisp-coder-110m

View all activity

Organizations

None yet

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-MTPLX-4bit about 1 month ago

Does it work with oMLX?

#1 opened 2 months ago by

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-bf16 about 2 months ago

Source for 711

#1 opened 2 months ago by

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-MTPLX-6bit about 2 months ago

You posted some raw TG numbers with/without MTP - do you happen to have TG/PP at higher contexts?

#1 opened 2 months ago by

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-bf16 about 2 months ago

The model works on a TPU (v5e-8) in vLLM.

#2 opened about 2 months ago by

New activity in multimodalart/minimax-h3 about 2 months ago

I make the video and then the page reloads

#8 opened about 2 months ago by

philipjohnbasile

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-ReducedRefusal-MTPLX-6bit about 2 months ago

Would it be worthwhile to provide links in the README.md to some of the source discussions/models?

#1 opened about 2 months ago by

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF about 2 months ago

VERSION: MLX / Apple Silicon conversions (working MTP + vision), plus a reconstructed bf16

#31 opened 2 months ago by

philipjohnbasile

New activity in philipjohnbasile/Qwen3.6-27B-Fable-Fusion-711-MTPLX-8bit about 2 months ago

Testing GGUF vs MTPLX on Mac m1 Max 64GB

#1 opened about 2 months ago by

EternalMoonshine

New activity in DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF 2 months ago

Abliteration not working

#13 opened 2 months ago by

VERSION: MLX --- Can we also get oMLX version? with MTP support plz

#37 opened 2 months ago by

New activity in huggingface/InferenceSupport 3 months ago

philipjohnbasile/GLM-5.2-Demolition-q3a4-MLX

#10587 opened 3 months ago by

philipjohnbasile

philipjohnbasile/GLM-5.2-Demolition-q3a4-MLX

#10586 opened 3 months ago by

philipjohnbasile

philipjohnbasile/GLM-5.2-Demolition-q3a4-MLX

#10586 opened 3 months ago by

philipjohnbasile

philipjohnbasile/GLM-5.2-Demolition-q3a4-MLX

#10586 opened 3 months ago by

philipjohnbasile