Score 41GGUF
16.5tps-Qwen3.5-122B-A10B-Q2_K_S
16 · Q2_K_S · language
largesmall
39.41 GBFile size
53.2 GBVRAM fit
8Downloads
2Votes
World catalog for AI community.
Powerful open models. Trusted signal. Faster discovery.
Top community interest
- Hugston_Lobotomized-LFM2.5-350M-f32.f163 votes · 5 downloads
- hugston-wangzhangQwen3.6-35B-A3B-abliterated-GGUF.Q4_K_M2 votes · 2 downloads
- High-quality-Qwen3.6-35B-A3B.Q4_K_M2 votes · 2 downloads
- 16.5tps-Qwen3.5-122B-A10B-Q2_K_S2 votes · 8 downloads
- Qwen3.5-122B-A10B-Opus-Reasoning-Q4_K_M1 votes · 3 downloads
363Cataloged model filesStructured discovery
51Hugston-tagged releasesCurated signal
32Vision-capable entriesMultimodal coverage
0Hot community signalsFresh ranking input
Most relevant now
Trending models
Ranked with catalog data and community signal.
Score 39GGUF
Hugston_Lobotomized-LFM2.5-350M-f32.f16
Hugston · F16 · language
hugston
0.66 GBFile size
2 GBVRAM fit
5Downloads
3Votes
Score 38GGUF
mythos-26b-a4b-prism-pro-dq
mythos · unknown · language
small
16.85 GBFile size
22.7 GBVRAM fit
5Downloads
0Votes
Score 40GGUF
Qwen3.5-122B-A10B-Opus-Reasoning-Q4_K_M
5 · Q4_K_M · language
largereasoningsmall
69.12 GBFile size
93.3 GBVRAM fit
3Downloads
1Votes
Score 43GGUF
hugston-wangzhangQwen3.6-35B-A3B-abliterated-GGUF.Q4_K_M
hugston · Q4_K_M · language
hugstonlargesmall
20.51 GBFile size
27.7 GBVRAM fit
2Downloads
2Votes
Score 43GGUF
High-quality-Qwen3.6-35B-A3B.Q4_K_M
High · Q4_K_M · language
largesmall
21.46 GBFile size
29 GBVRAM fit
2Downloads
2Votes
Editorial layer
AI news and analysis
Original writing and commentary that turns updates into useful context.
Operator-grade path
HugstonOne Enterprise
Work, create, write, study, research, educate, with privacy.
A Workflow/Software for AI inference
Image, PDF, CSV, audio, video, txt, html...100+ types file processing, Deep research with online mode, Retrieval-augmented generation (RAG), Advanced agents running 24/7 in Cli fully locally, Offline/Online Mode for model and data isolation, Load LLM Models in CLI, SERVER or both same time, GPU / CPU support, Instant Preview of the code, Code Editior also with preview, GGUF support 10000+ LLM Models, Session and minisessions with persistent memory, User data memory with option On/Off,
Privacy, local first
Fully local and private, Terminal for advanced users, Export tables in CSV and save sessions/tabs/preview, Easy to create Webpages/Graphic interfaces/3d modeling, Great for creating games, tables, maps with data, charts, plots, Good coding assistant (hopping from tab to tab, conserving memory, solving the ctx size and memory issue), Live news feed on the app while working (can retrieve all TV/news/radio/podcast feeds) while working, Ideal for Research (with free medical models available from HuggingFace or Hugston.com), Local Api with proper engine, AI-powered diagnostics for X-rays, MRI, drawings, 3D modeling, etc. (via Image-to-Text).
Our Strongest Points
We don’t collect user data No forced updates included in the app, No telemetry, No HTTP involved (load with local CLI), Fully standalone, no other dependencies to install, 1 click Install (Windows), No internet required unless explicitly chosen by the user, No API key required, Supports long lines of code Input/Output (50000+ tokens tested/tab), No refusal Using the right LLM model (potential for 200,000+ code lines, divided into 1000-5000-20000 lines at once), Completely free.