Instructions to use t-tech/T-pro-it-2.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use t-tech/T-pro-it-2.1-GGUF 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 t-tech/T-pro-it-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf t-tech/T-pro-it-2.1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf t-tech/T-pro-it-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf t-tech/T-pro-it-2.1-GGUF:Q4_K_M

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 t-tech/T-pro-it-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf t-tech/T-pro-it-2.1-GGUF:Q4_K_M

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 t-tech/T-pro-it-2.1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf t-tech/T-pro-it-2.1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/t-tech/T-pro-it-2.1-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use t-tech/T-pro-it-2.1-GGUF with Ollama:
```
ollama run hf.co/t-tech/T-pro-it-2.1-GGUF:Q4_K_M
```

Unsloth Studio

How to use t-tech/T-pro-it-2.1-GGUF 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 t-tech/T-pro-it-2.1-GGUF 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 t-tech/T-pro-it-2.1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for t-tech/T-pro-it-2.1-GGUF to start chatting

How to use t-tech/T-pro-it-2.1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf t-tech/T-pro-it-2.1-GGUF:Q4_K_M

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": "t-tech/T-pro-it-2.1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use t-tech/T-pro-it-2.1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf t-tech/T-pro-it-2.1-GGUF:Q4_K_M

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 "t-tech/T-pro-it-2.1-GGUF:Q4_K_M" \
  --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 t-tech/T-pro-it-2.1-GGUF with Docker Model Runner:
```
docker model run hf.co/t-tech/T-pro-it-2.1-GGUF:Q4_K_M
```

Lemonade

How to use t-tech/T-pro-it-2.1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull t-tech/T-pro-it-2.1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.T-pro-it-2.1-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use t-tech/T-pro-it-2.1-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf t-tech/T-pro-it-2.1-GGUF:Q4_K_M

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 t-tech/T-pro-it-2.1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

T-pro-it-2.1-GGUF

🚨 Users are advised to exercise caution and are responsible for any additional training and oversight required to ensure the model's responses meet acceptable ethical and safety standards. The responsibility for incorporating this model into industrial or commercial solutions lies entirely with those who choose to deploy it.

This repository contains T-pro-it-2.1 converted to the GGUF format with llama.cpp.
See the original BF16 model here: t-tech/T-pro-it-2.1.

Description

T-pro-it-2.1 — is an efficient russian model built upon the Qwen 3 model family with improved instruction following and tool-calling capabilities compared to T-pro-it-2.0. Outperforms Qwen3-32B in tool calling scenarios, which is essential for agentic applications. Built for both general tasks and complex workflows.

NOTE: This model supports only non-thinking mode and does not generate <think></think> blocks in its output. Meanwhile, specifying enable_thinking=False is no longer required.

📊 Benchmarks

	Ru Arena Hard	ruIFeval*	ruBFCL
T-pro-it-2.1	93.8	80.7	66.0
T-pro-it-2.1-Q8_0	94.2	80.8	65.8
T-pro-it-2.1-Q6_K	93.4	80.0	65.9
T-pro-it-2.1-Q5_K_M	92.7	81.4	65.7
T-pro-it-2.1-Q5_K_S	92.3	80.4	65.2
T-pro-it-2.1-Q5_0	93.8	79.9	64.8
T-pro-it-2.1-Q4_K_M	92.6	80.7	64.8

* IFeval metric is mean of 4 values: prompt and instruct levels for strict and loose accuracy.

Recommendation: choose the highest-quality quantisation that fits your hardware (VRAM / RAM).

Filename (→ `-gguf`)	Quant method	Bits	Size (GB)
`T-pro-it-2.1-q8_0`	Q8_0	8	34.8
`T-pro-it-2.1-q6_k`	Q6_K	6	26.9
`T-pro-it-2.1-q5_k_m`	Q5_K_M	5	23.2
`T-pro-it-2.1-q5_k_s`	Q5_K_S	5	22.6
`T-pro-it-2.1-q5_0`	Q5_0	5	22.6
`T-pro-it-2.1-q4_k_m`	Q4_K_M	4	19.8

Size figures assume no GPU off-loading. Off-loading lowers RAM usage and uses VRAM instead.

Quickstart

llama.cpp

Check out our llama.cpp documentation for more usage guide.

We advise you to clone llama.cpp and install it following the official guide. We follow the latest version of llama.cpp. In the following demonstration, we assume that you are running commands under the repository llama.cpp.

./llama-cli -hf t-tech/T-pro-it-2.1-GGUF:Q8_0 --jinja --color -ngl 99 -fa -sm row --temp 0.6 --presence-penalty 1.0 -c 40960 -n 32768 --no-context-shift

ollama

Check out our ollama documentation for more usage guide.

You can run T-pro-2.1 with one command:

ollama run t-tech/T-pro-it-2.1:q8_0

Model tree for t-tech/T-pro-it-2.1-GGUF

Base model

Qwen/Qwen3-32B

Finetuned

t-tech/T-pro-it-2.1

Quantized

(6)

this model

Collection including t-tech/T-pro-it-2.1-GGUF

T-pro-2.1

Collection

3 items • Updated Dec 23, 2025 • 9