govai 2.4

A small, fast AI assistant that runs on your own computer. Free, open and private.

govai answers in plain words, writes full step-by-step guides when you ask for detail, solves maths and science problems, and can think before answering hard questions. New in 2.4: tool calling. Give govai tools (search your files, a calculator, any API) and it decides by itself when to call one, and answers directly when none fits. One 1.3 GB file, fully offline.

Size	~2B parameters · govai-2.4-q4_k_m.gguf · 1.31 GB (Q4_K_M)
Context	16,384 tokens recommended
Tools	OpenAI-style function definitions (Ollama tools, llama.cpp --jinja)
Languages	English (best), Hindi, Telugu
Speed	~150 tokens/s on a gaming GPU; usable on CPU
License	Apache 2.0 · by govai labs

Benchmarks

All scores: the Q4_K_M file above, temperature 0, unfinished answers counted as wrong, and no test question used in training (8-word overlap check).

Tool calling	govai 2.3	govai 2.4
BFCL v3 · one call (100)	21%	85%
BFCL v3 · pick the right tool (100)	38%	85%
BFCL v3 · several calls at once (100)	6%	78%
BFCL v3 · no tool fits, don't call (100)	95%	85%
BFCL v3 · average	40.0%	83.2%
Your files: right tool (search / list / read, 20)	12/20	20/20
Your files: answer uses what the tool returned (20)	8/20	19/20

The file test uses made-up computers; half of its questions use file kinds that never appeared in training (insurance policy, salary slip, blood test).

Same questions, thinking off	govai 2.3	govai 2.4
GSM8K · school maths (250)	82.8%	82.4%
ARC-Challenge · science (300)	83.0%	83.3%
MMLU · knowledge (400)	61.5%	61.8%

Maths, science and knowledge stay level with govai 2.3 (differences are within ±5 points).

Use it

ollama run hf.co/govailabs/govai:Q4_K_M          # Ollama
llama-cli -hf govailabs/govai --jinja            # llama.cpp

Tool calling (Ollama, Python)

import ollama

tools = [{"type": "function", "function": {
    "name": "search_files",
    "description": "Search the user's files by words in the file name.",
    "parameters": {"type": "object", "properties": {"query": {"type": "string"}}, "required": ["query"]}}}]

reply = ollama.chat(model="hf.co/govailabs/govai:Q4_K_M", think=False, tools=tools,
                    messages=[{"role": "user", "content": "Where is my resume?"}])
print(reply.message.tool_calls)   # [search_files(query="resume")]
# Run the tool, add {"role": "tool", "content": <result>} to the messages, and ask again for the answer.

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama.from_pretrained(repo_id="govailabs/govai", filename="govai-2.4-q4_k_m.gguf", n_ctx=16384)
reply = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": "You are govai, a friendly and helpful AI assistant. Answer clearly in simple words."},
        {"role": "user", "content": "Explain how vaccines work."},
    ],
    temperature=0.3, top_p=0.9, top_k=20,
)
print(reply["choices"][0]["message"]["content"])

Settings: temperature 0.3 (0 for maths and tool calls), top_p 0.9, top_k 20. Turn thinking on (think: true in Ollama) for hard problems and give it room (4,096+ tokens). Ask "explain fully" or "step by step" for a complete guide; short questions get short answers.

govai for Windows

Download govai-setup-windows.exe (183 MB, Windows 10/11 64-bit). Chat with this model fully on your PC, with web search and sources, your own files (govai can find, list and read documents, PDFs and spreadsheets in your personal folders when a question needs it: read-only, and it shows which files it opened), a built-in calculator, memory, light and dark themes, and updates inside the app. The installer isn't code-signed yet: if Windows says "Windows protected your PC", click More info → Run anyway.

SHA-256: 963ebdd1b1e311a67bf1a77892fd3ef66d6f0edb1789025afb0d4206eab56b24

Limitations

• A small model: it can get facts wrong, especially about people, places, dates and recent events. The govai app searches the web for those; on its own, check important facts.
• Tool calls can still be wrong or missing an argument; check what a tool will do before running it, and give govai read-only tools where you can.
• Hindi and Telugu answers are weaker than English ones.
• Very hard problems (competition maths, graduate science) need thinking on and a long budget.
• Not for professional medical, legal or financial advice.

License

Apache 2.0 (LICENSE), provided "as is". Open-source notices are in NOTICE.

Citation

@misc{govai2026,
  title  = {govai 2.4: a small, fast, private AI assistant with tool calling},
  author = {govai labs},
  year   = {2026},
  url    = {https://huggingface.co/govailabs/govai}
}