Instructions to use theycallmedan14/hiveai-v5-think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use theycallmedan14/hiveai-v5-think with 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 theycallmedan14/hiveai-v5-think
# Run inference directly in the terminal:
llama cli -hf theycallmedan14/hiveai-v5-think

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf theycallmedan14/hiveai-v5-think
# Run inference directly in the terminal:
llama cli -hf theycallmedan14/hiveai-v5-think

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf theycallmedan14/hiveai-v5-think
# Run inference directly in the terminal:
./llama-cli -hf theycallmedan14/hiveai-v5-think

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf theycallmedan14/hiveai-v5-think
# Run inference directly in the terminal:
./build/bin/llama-cli -hf theycallmedan14/hiveai-v5-think

Use Docker

docker model run hf.co/theycallmedan14/hiveai-v5-think

LM Studio
Jan
Ollama
How to use theycallmedan14/hiveai-v5-think with Ollama:
```
ollama run hf.co/theycallmedan14/hiveai-v5-think
```

Unsloth Studio

How to use theycallmedan14/hiveai-v5-think with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for theycallmedan14/hiveai-v5-think to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for theycallmedan14/hiveai-v5-think to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for theycallmedan14/hiveai-v5-think to start chatting

How to use theycallmedan14/hiveai-v5-think with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theycallmedan14/hiveai-v5-think

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "theycallmedan14/hiveai-v5-think"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use theycallmedan14/hiveai-v5-think with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theycallmedan14/hiveai-v5-think

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "theycallmedan14/hiveai-v5-think" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use theycallmedan14/hiveai-v5-think with Docker Model Runner:
```
docker model run hf.co/theycallmedan14/hiveai-v5-think
```

Lemonade

How to use theycallmedan14/hiveai-v5-think with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull theycallmedan14/hiveai-v5-think

Run and chat with the model

lemonade run user.hiveai-v5-think-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use theycallmedan14/hiveai-v5-think with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf theycallmedan14/hiveai-v5-think

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default theycallmedan14/hiveai-v5-think

Run Hermes

hermes

Atomic Chat

HiveAI v5-think

Fine-tuned Qwen2.5-Coder-14B for multi-language code generation. 94.30% on 60-probe eval (6 domains).

Download

wget https://huggingface.co/theycallmedan14/hiveai-v5-think/resolve/main/current_base.gguf -O hiveai-v5-think.gguf

Run

./llama-server -m hiveai-v5-think.gguf --host 0.0.0.0 --port 11435 -ngl 99 --flash-attn auto -c 8192 --parallel 2 -cb

Scores (2026-03-22)

Domain	Score
C++	93.25%
Go	96.80%
Hive	95.50%
JS	93.80%
Python	92.83%
Rust	93.65%
Overall	94.30%

Join the GPU Pool

This model powers HiveAI + HivePoA. More GPUs = smarter system.

Downloads last month: 11

GGUF

Model size

15B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for theycallmedan14/hiveai-v5-think

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-Coder-14B

Finetuned

Qwen/Qwen2.5-Coder-14B-Instruct

Quantized

(117)

this model