Instructions to use RefinedNeuro/RefinedToolCallV5-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RefinedNeuro/RefinedToolCallV5-3b with HERMES:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

llama-cpp-python

How to use RefinedNeuro/RefinedToolCallV5-3b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RefinedNeuro/RefinedToolCallV5-3b",
	filename="RefinedToolCallV5-3b-Q6_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RefinedNeuro/RefinedToolCallV5-3b 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 RefinedNeuro/RefinedToolCallV5-3b:Q6_K
# Run inference directly in the terminal:
llama cli -hf RefinedNeuro/RefinedToolCallV5-3b:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RefinedNeuro/RefinedToolCallV5-3b:Q6_K
# Run inference directly in the terminal:
llama cli -hf RefinedNeuro/RefinedToolCallV5-3b:Q6_K

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 RefinedNeuro/RefinedToolCallV5-3b:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf RefinedNeuro/RefinedToolCallV5-3b:Q6_K

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 RefinedNeuro/RefinedToolCallV5-3b:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RefinedNeuro/RefinedToolCallV5-3b:Q6_K

Use Docker

docker model run hf.co/RefinedNeuro/RefinedToolCallV5-3b:Q6_K

LM Studio
Jan

vLLM

How to use RefinedNeuro/RefinedToolCallV5-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RefinedNeuro/RefinedToolCallV5-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RefinedNeuro/RefinedToolCallV5-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RefinedNeuro/RefinedToolCallV5-3b:Q6_K

Ollama
How to use RefinedNeuro/RefinedToolCallV5-3b with Ollama:
```
ollama run hf.co/RefinedNeuro/RefinedToolCallV5-3b:Q6_K
```

Unsloth Studio

How to use RefinedNeuro/RefinedToolCallV5-3b 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 RefinedNeuro/RefinedToolCallV5-3b 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 RefinedNeuro/RefinedToolCallV5-3b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RefinedNeuro/RefinedToolCallV5-3b to start chatting

How to use RefinedNeuro/RefinedToolCallV5-3b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RefinedNeuro/RefinedToolCallV5-3b:Q6_K

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": "RefinedNeuro/RefinedToolCallV5-3b:Q6_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use RefinedNeuro/RefinedToolCallV5-3b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RefinedNeuro/RefinedToolCallV5-3b:Q6_K

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 RefinedNeuro/RefinedToolCallV5-3b:Q6_K

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use RefinedNeuro/RefinedToolCallV5-3b with Docker Model Runner:
```
docker model run hf.co/RefinedNeuro/RefinedToolCallV5-3b:Q6_K
```

Lemonade

How to use RefinedNeuro/RefinedToolCallV5-3b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RefinedNeuro/RefinedToolCallV5-3b:Q6_K

Run and chat with the model

lemonade run user.RefinedToolCallV5-3b-Q6_K

List all available models

lemonade list

🛠️🧠 RefinedToolCall-V5-3B

A 3B model that reasons and calls tools — and actually holds a multi-turn conversation.

Math-grade reasoning · real function calling · multi-turn agentic · 2.5 GB · runs on your laptop.

ollama run refinedneuro/refinedtoolcallv5-3b

Why it's different

Most 3B tool-callers nail a single function call and then fall apart the moment the task spans several turns. RefinedToolCall-V5 was built specifically to fix that — and the numbers moved on every axis at once, not just the one we were targeting.

🔁 Multi-turn agentic that actually works — ~3.7× better at stateful, multi-step tool-use (Berkeley Function-Calling Leaderboard multi_turn) than where we started.
🛠️ Sharper single-turn calling — 70.7% on BFCL single-turn (held-out), our best ever.
💪 Recovers from tool errors — 0.896 recovery rate; it diagnoses failures instead of looping on them.
🧮 Reasoning fully intact — AIME-2024 pass@8 0.933, unchanged by all the tool training.
⚡ Tiny & local — 3B params, 2.5 GB Q6_K, one command on Ollama, no GPU required.
🆓 Apache-2.0 — use it, ship it, fine-tune it.

The receipts (all held-out, canary-gated)

capability	this model
🔁 Multi-turn agentic (BFCL `multi_turn`, k=3)	0.220 avg / 0.298 pass@3
🛠️ Single-turn function calling (BFCL, held-out)	0.707
🩹 Recovery from tool errors (n=250)	0.896
🧮 Reasoning (AIME-2024 pass@8)	0.933

Every number is the best across five fine-tuning rounds — multi-turn, single-turn, recovery, and reasoning all peaked together.

How we got here (and why it generalizes)

We didn't just throw data at it. Five disciplined rounds, each one gated so it could never regress reasoning or recovery:

Grounding — stop inventing shell commands; call the actual functions.
Plan + finish — think before calling, and know when the turn is done.
Scale + long context — harder tasks, up to 24k tokens.
On-policy self-improvement (the breakthrough) — the model learns from its own successful multi-turn solutions (expert iteration), which broke past the imitation ceiling and sharpened single-turn calling and error-recovery as a bonus.

Quick start

Ollama

ollama run refinedneuro/refinedtoolcallv5-3b      # latest = Q6_K, 2.5 GB

💡 Use Q6_K or higher for tool-calling — lower quants corrupt the call tokens.

Format: ChatML + Hermes tools. Each turn the model emits a <think> plan → one or more <tool_call> blocks → a final reply. Recommended: temp 0.6, top_p 0.95, repeat_penalty 1.1.

Great for

✅ Local/offline agentic tool-use prototypes ✅ Multi-step function-calling assistants ✅ Math & STEM reasoning ✅ Learning how small agentic models are actually built.

Be honest with me (research preview)

⚠️ It's a 3B research preview. Multi-turn is dramatically improved (~3.7×) but not solved — very long, open-ended autonomous loops can still write buggy code or mis-plan. A brilliant, tiny building block; not yet a drop-in autonomous engineer.

Built on WeiboAI/VibeThinker-3B + lambda/hermes-agent-reasoning-traces. Trained with distribution-matched RFT + on-policy expert iteration, every checkpoint gated against reasoning/recovery canaries. Apache-2.0.

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for RefinedNeuro/RefinedToolCallV5-3b

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

WeiboAI/VibeThinker-3B

Quantized

(49)

this model

RefinedNeuro
/

RefinedToolCallV5-3b