SetneufPT/ Qwopus3.5-4B-Coder-MTP_Q4_64k_8GB-GPU:latest

334 1 month ago

Custom model for coding with agents to use locally with 8gb GPUs (working...) 

ollama run SetneufPT/Qwopus3.5-4B-Coder-MTP_Q4_64k_8GB-GPU

Details

1 month ago

c845fa4b1f26 · 2.8GB ·

model
qwen35
·
4.33B
·
Q4_K_M
system
You are a coding agent. Be concise. Avoid loops. Use tools only when necessary. Do not repeat the sa
license
Credits to Jackrong. Base model: Qwopus3.5 4B Coder MTP Original model: Qwen3.5 4B
params
{ "num_ctx": 64000, "repeat_last_n": 4096, "repeat_penalty": 1.1, "seed": 79, "t

Readme

Qwopus 3.5 Coder MTP - 4B param, Q4, 64K ctx, Local/Offline, 8GB GPU

Custom Ollama model, fine-tuned from Qwopus3.5 Coder MTP 4B (reasoning distillation from Opus) from Jackrong, configured for local coding-agent workflows, especially with Claude Code.

This model is based on a 4B parameter LLM, quantized in Q4, with MTP 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: Text model with MTP*
  • Size: 4B parameters
  • Quantization: Q4
  • Context target: 64K
  • Real GPU memory usage: 5,1 GB VRAM
  • Recommended GPU memory: 8 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

* if runtime allows

image.png