SetneufPT/ Ornith-1.0-35B-MOE_Q4_200k_32GB-GPU:latest

30 2 weeks ago

Custom model for coding with agents to use locally with 32gb, 2x16gb or 5x8gb GPUs (working very well!!) 

ollama run SetneufPT/Ornith-1.0-35B-MOE_Q4_200k_32GB-GPU

Details

2 weeks ago

9e49b598ce0c · 21GB ·

model
qwen35moe
·
34.7B
·
Q4_K_M
license
MIT License Copyright (c) [year] [fullname] Permission is hereby granted, free of charge, to any per
system
Você é o Claude Code, um assistente de inteligência artificial de elite especializado em engenhar
params
{ "num_ctx": 200000, "num_predict": 8096, "stop": [ "<|im_end|>" ], "tem
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user

Readme

Ornith 1.0 - 35B param MOE, Q4, 200K ctx, Local/Offline, 32GB (or 2x 16GB) GPU

Custom Ollama model, tuned from Ornith 1.0 from DeepReinforce-AI, configured for local coding-agent workflows, especially with Claude Code.

This model is based on a 35B parameter Mixture of Experts (MOE) LLM, quantized in Q4, and configured with a large context window for software development tasks. It is intended to provide a practical balance between performance, memory usage, and code-assistance quality on local hardware.

Model details

  • Type: Textmodel
  • Size: 35B parameters MOE
  • Quantization: Q4
  • Context target: 200K
  • Real GPU memory usage: 29 GB VRAM
  • Recommended GPU memory: 32 GB VRAM
  • Main focus: Coding and agentic development workflows
  • Tool use: Supported, depending on the client/application
  • Thinking/reasoning mode: Supported, depending on the client/application

Intended use

This model is designed for:

  • Agents workflows
  • Local coding assistants
  • Code analysis
  • Debugging support
  • Refactoring suggestions
  • Project exploration
  • Terminal-based programming tasks
  • Educational demonstrations of AI coding agents

image.png