Etherworld RP
1 Pull 1 Tag Updated 4 hours ago
A copy by author Igorls from hf. I tested it, the quality is excellent! 👍👍👍
1 Pull 1 Tag Updated 8 hours ago
A copy by author TrevorJS from hf. I tested it, the quality is excellent! 👍👍👍
5 Pulls 1 Tag Updated 9 hours ago
Avec mAI-1.2-Light, discutez ou codez rapidement !
1 Pull 1 Tag Updated 9 hours ago
Avec mAI-1.2-Opal, discutez ou codez rapidement !
1 Pull 1 Tag Updated 10 hours ago
The local code-locator delegate for grove’s delegated exploration mode.
3 Pulls 3 Tags Updated 12 hours ago
1 Tag Updated 18 hours ago
Custom model for coding with agents to use locally with 16gb GPUs (working very fine...)
80 Pulls 1 Tag Updated yesterday
2 Pulls 3 Tags Updated yesterday
basado en qwen3.5, con 1 Millon de contexto + Entrenado con datos de Mythos Para codigo y razonamiento
33 Pulls 1 Tag Updated yesterday
Contexto de 1 Millon, Sin censura y basado en qwen3.5
52 Pulls 1 Tag Updated yesterday
Pruned to 184e version of 35b-a3b with LCB and MultiPL-E HE targeting for Coding
65 Pulls 47 Tags Updated 2 hours ago
Enterprise coding & engineering assistant by GOCOSYS Technologies — built on Qwen2.5-Coder-7B. Great for PHP, Laravel, Python, JS/TS, React, Node, Docker & DevOps.
26 Pulls 1 Tag Updated yesterday
AI agent trained in code, logic, and defensive cybersecurity
6 Pulls 2 Tags Updated 2 days ago
The customizable version of Omega9, a sleeper agent model
1 Tag Updated 2 days ago
Parable is a family of open models trained on real Claude Fable 5 and GPT-5.5 agent traces for local agentic coding. Best model per size; Qwen3 and IBM Granite lines.
146 Pulls 6 Tags Updated yesterday
**MidnightCoder-80B** coding model for the Midnight Coder AI coding agent. Optimized for local software engineering with SmartContext (~45% prompt context reduction). Install the agent with `npm install -g midnight-coder`.
17 Pulls 1 Tag Updated 2 days ago
**MidnightCoder-30B** coding model for the Midnight Coder Agent with SmartContext (~45% less prompt context). Install: `npm install -g midnight-coder` • Run: `ollama run midnightcoderagent/MidnightCoder-30B`
117 Pulls 1 Tag Updated 2 days ago
qwen3:4b tuned for tool calling — the prompt and decoding settings that make a 4B model actually call the tool instead of pretending it did.
10 Pulls 1 Tag Updated 3 days ago
A custom merged model: the vision layers were borrowed from Mistral-3 and joined with Bielik-7B (SpeakLeash). The result is a compact multimodal model that reads text from images — printed pages, scans.
13 Pulls 1 Tag Updated 3 days ago