Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

On-device and local LLMs on Apple Silicon (MLX), small calibrated decision models, fact-checking and content quality for long-running websites, and open-source tooling for small teams.

Recent Activity
Paris99  updated a model 2 days ago
netprojects/Nemotron-3.5-Rerank-8B-GGUF
Paris99  published a model 2 days ago
netprojects/Nemotron-3.5-Rerank-8B-GGUF
Paris99  updated a Space 4 days ago
netprojects/README
View all activity

Organization Card
Community About org cards

NetProjects

Open models, ready to run on Apple Silicon.

We convert and test open models for MLX, so they run locally on a Mac with no cloud and no API keys. We check every build against the original model before it goes up, and we publish speed numbers from real hardware (MacBook Pro M5 Max, 128 GB).

Models

Family Builds What it's for
Fastino GLiDE 26B 8-bit · 4-bit Calibrated decision model (choice / yes-no / score), full-attention reading
H2O-Lightning 4B q8 · q4 Small calibrated decision model from H2O.ai (text and images, two-way reading, Box questions)
IBM Granite Switch 4.1 8B 8-bit · 4-bit — 30B 8-bit · 4-bit IBM Granite with switchable chat, decision and guardian modes
NVIDIA Nemotron Dory 1.0 4B 8-bit · bf16 Looped reasoning LM from NVIDIA Nemotron Labs
NVIDIA Nemotron 3.5 Embed / Rerank Embed-1B bf16 · 8-bit — Embed-8B 8-bit · 4-bit — Rerank-8B 8-bit · 4-bit Retrieval: embeddings and reranking for text and page images (scores match NVIDIA's published ViDoRe v3 results)
AutoTrust JEV-35B 8-bit · 4-bit mixed · 3-bit mixed AutoTrust decision and classification model
AutoTrust-JEV-27B v1.1 8-bit · 4-bit Decision model with bidirectional prompt reading (custom loader included)

How we build

  • Conversions use the standard mlx-lm / mlx-vlm tools; where a model needs custom code, the loader is open source on GitHub.
  • Each card says which upstream revision it was built from, how it was quantized and how it was checked, with speed and memory measured on an M5 Max.
  • Licences follow the original model.

Code

All builds in one place: NetProjects MLX builds collection.

Also

We also work on small calibrated decision models, fact-checking and content quality for long-running websites, and open-source tooling for small teams.

Spotted a problem or want a model converted? Open a discussion on any model page.

Collections 1

NetProjects MLX builds
Open models converted and tested for Apple Silicon (MLX) by NetProjects, each checked against the original model.
NetProjects MLX builds
Open models converted and tested for Apple Silicon (MLX) by NetProjects, each checked against the original model.

datasets 0

None public yet