How to use from
llama.cpp
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sazid63/archresidencebd-models:Q8_0
# Run inference directly in the terminal:
llama cli -hf sazid63/archresidencebd-models:Q8_0
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sazid63/archresidencebd-models:Q8_0
# Run inference directly in the terminal:
llama cli -hf sazid63/archresidencebd-models:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf sazid63/archresidencebd-models:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf sazid63/archresidencebd-models:Q8_0
Use Docker
docker model run hf.co/sazid63/archresidencebd-models:Q8_0
Quick Links
ArchResidenceBD model fleet banner

Model fleet ready GGUF format llama.cpp runtime

Open model fleet for AI-assisted residential building workflows in Bangladesh.


ArchResidenceBD Model Fleet

This repository contains the model fleet for ArchResidenceBD β€” an AI civil engineer for Bangladeshi residential buildings.

The collection includes quantized GGUF models optimized for local inference with llama.cpp, designed to support workflow tasks such as:

  • building interviews and structured reasoning
  • repair and debugging assistance for CAD-related scripts
  • retrieval and reranking for contextual document search
  • practical research workflows for Bangladesh-specific residential design problems

Models

Model Role Base Quantization Size Purpose
archie-chat-v0-Q4_K_M.gguf Chat Qwen3-4B-Instruct-2507 Q4_K_M 2.33 GB Interview, explanation, structured reasoning
archres-repair-v0-Q4_K_M.gguf Repair Qwen2.5-Coder-3B-Instruct Q4_K_M 1.80 GB CAD script repair and technical troubleshooting
Qwen3-Embedding-0.6B-Q8_0.gguf Embedding Qwen3-Embedding-0.6B Q8_0 0.60 GB Retrieval and embedding generation
Qwen3-Reranker-0.6B-Q8_0.gguf Reranker Qwen3-Reranker-0.6B Q8_0 0.60 GB Re-ranking retrieved results

Usage

All models are distributed in GGUF format and are intended for use with llama.cpp.

# Chat model
llama-server -m archie-chat-v0-Q4_K_M.gguf -ngl 99 -c 8192

# Repair model
llama-server -m archres-repair-v0-Q4_K_M.gguf -ngl 99 -c 8192

# Embedding model
llama-server -m Qwen3-Embedding-0.6B-Q8_0.gguf -ngl 0 --embeddings --pooling last

# Reranker model
llama-server -m Qwen3-Reranker-0.6B-Q8_0.gguf -ngl 0 --reranking
Downloads last month
497
GGUF
Model size
4B params
Architecture
qwen3
Hardware compatibility
Log In to add your hardware

4-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support