Instructions to use alekringtonnn-ai/zubr-mini-1.9-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alekringtonnn-ai/zubr-mini-1.9-3b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="alekringtonnn-ai/zubr-mini-1.9-3b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("alekringtonnn-ai/zubr-mini-1.9-3b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use alekringtonnn-ai/zubr-mini-1.9-3b 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 alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alekringtonnn-ai/zubr-mini-1.9-3b: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 alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf alekringtonnn-ai/zubr-mini-1.9-3b: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 alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M

Use Docker

docker model run hf.co/alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M

LM Studio
Jan

vLLM

How to use alekringtonnn-ai/zubr-mini-1.9-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alekringtonnn-ai/zubr-mini-1.9-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alekringtonnn-ai/zubr-mini-1.9-3b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M

SGLang

How to use alekringtonnn-ai/zubr-mini-1.9-3b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "alekringtonnn-ai/zubr-mini-1.9-3b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alekringtonnn-ai/zubr-mini-1.9-3b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "alekringtonnn-ai/zubr-mini-1.9-3b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alekringtonnn-ai/zubr-mini-1.9-3b",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use alekringtonnn-ai/zubr-mini-1.9-3b with Ollama:
```
ollama run hf.co/alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M
```
Unsloth Desktop

How to use alekringtonnn-ai/zubr-mini-1.9-3b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use alekringtonnn-ai/zubr-mini-1.9-3b with Docker Model Runner:
```
docker model run hf.co/alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M
```

Lemonade

How to use alekringtonnn-ai/zubr-mini-1.9-3b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M

Run and chat with the model

lemonade run user.zubr-mini-1.9-3b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use alekringtonnn-ai/zubr-mini-1.9-3b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alekringtonnn-ai/zubr-mini-1.9-3b: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 alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use alekringtonnn-ai/zubr-mini-1.9-3b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alekringtonnn-ai/zubr-mini-1.9-3b: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 "alekringtonnn-ai/zubr-mini-1.9-3b: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"

🦬 Zubr Mini 1.9 3B

Repository: alekringtonnn-ai/zubr-mini-1.9-3b

📖 What This Model Is

zubr-mini-1.9-3b is a multimodal (Vision) language model with 3 billion parameters, fine-tuned from Mistral 3 3B (Ministral-3-3B-Instruct-2512 by Mistral AI). Developed by alekringtonnn-ai.

The model is distributed in GGUF format — a universal format for quantized weights designed for local inference. It runs on regular PCs (CPU), laptops, mobile devices, and servers without expensive GPUs.

💡 For Macs with Apple Silicon (M1–M4), there is a separate MLX version of this same model: alekringtonnn-ai/zubr-mini-1.9-3b-mlx.

Key Features

Multimodal (Vision): the model supports image recognition and Image-Text-to-Text tasks (image + text → text).
Multilingual: language support expanded from 26 to 48 languages (including Russian).
Performance: improved vocabulary, high inference speed, and deep instruction tuning.
Local execution: the GGUF format runs on CPU and GPU via Ollama, llama.cpp, vLLM, LM Studio, and other runtimes.
License: Apache 2.0 — free to use, including for commercial purposes.

Model Tree

mistralai/Ministral-3-3B-Base-2512
        │ (quantization / instruct version)
mistralai/Ministral-3-3B-Instruct-2512
        │
mistralai/Ministral-3-3B-Instruct-2512-GGUF
        │ (fine-tune by alekringtonnn-ai)
alekringtonnn-ai/zubr-mini-1.9-3b          ← GGUF version (THIS repository)
        │ (conversion to MLX)
alekringtonnn-ai/zubr-mini-1.9-3b-mlx       ← MLX version for Apple Silicon

📊 Versions (Quantizations) in the Repository

The repository offers 8 GGUF quantization options — from an ultra-compact 2-bit one to a nearly original 8-bit one:

Version	File	Size	What it is	What it's for
Q2_K	zubr-mini-1.9.Q2_K.gguf	~1.46 GB	The most aggressive 2-bit quantization	Devices with minimal memory (~4 GB RAM). Quality suffers noticeably
Q2_K_L	zubr-mini-1.9.Q2_K_L.gguf	~1.56 GB	An improved 2-bit quantization with larger high-precision layers	Same as Q2_K, but with slightly higher quality in certain layers
IQ3_XS	zubr-mini-1.9.IQ3_XS.gguf	~1.58 GB	Intelligent 3-bit quantization (IQ) — more compact than classic 3-bit	Low-power devices (~6 GB RAM): better than Q2, smaller than Q3_K_L
Q3_K_L	zubr-mini-1.9.Q3_K_L.gguf	~1.93 GB	3-bit quantization with large high-precision layers	Devices with limited memory (~8 GB RAM) — a quality/size balance
Q4_0	zubr-mini-1.9.Q4_0.gguf	~2.05 GB	Classic 4-bit quantization (fast, simple format)	A well-established legacy format: high speed, ~8 GB RAM
Q4_K_M ⭐	zubr-mini-1.9.Q4_K_M.gguf	~2.15 GB	4-bit quantization with medium high-precision layers	The recommended choice for most users: near-full quality at only ~2.15 GB
Q6_K	zubr-mini-1.9.Q6_K.gguf	~2.82 GB	6-bit quantization — high quality	For tasks where quality matters (e.g., RAG, precise answers). Requires ~12 GB RAM
Q8_0	zubr-mini-1.9.Q8_0.gguf	~3.65 GB	8-bit quantization — virtually lossless quality	Maximum quality with no performance loss. Requires ~16 GB RAM

💡 How to choose: the standard recommendation is Q4_K_M (quality/size balance). If memory is tight — Q3_K_L or IQ3_XS; if you need maximum quality — Q6_K or Q8_0.

📥 How to Download

Requirements

A CPU with AVX/AVX2 support (almost any modern x86) or an ARM device; a GPU is optional.
RAM: at least twice the size of the quantization file (see the table above).
Free disk space: 1.5–3.7 GB depending on the version.
For vLLM — an NVIDIA GPU (or Apple Silicon) and Linux/macOS.

Method 1: Ollama (the easiest)

# Install Ollama: https://ollama.com
# The recommended version:
ollama run hf.co/alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M

# Other quantizations — just change the tag:
ollama run hf.co/alekringtonnn-ai/zubr-mini-1.9-3b:Q2_K
ollama run hf.co/alekringtonnn-ai/zubr-mini-1.9-3b:Q8_0

Ollama will automatically download the required GGUF file and start a chat in your terminal.

Method 2: llama.cpp

# The recommended version — download and run in one command:
llama-cli -hf alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M

# Or download the file and specify it explicitly:
llama-cli -m zubr-mini-1.9.Q4_K_M.gguf -p "Hello! Tell me about yourself."

Method 3: `huggingface-cli` (direct file downloads)

# Install the CLI
pip install -U "huggingface_hub[cli]"

# Download a specific quantization:
huggingface-cli download alekringtonnn-ai/zubr-mini-1.9-3b \
  zubr-mini-1.9.Q4_K_M.gguf

# Download the entire repository (all 8 quantizations, ~17 GB):
huggingface-cli download alekringtonnn-ai/zubr-mini-1.9-3b

By default, files are saved to ~/.cache/huggingface/hub/.

Method 4: Direct links (browser / wget / curl)

curl -L -o zubr-mini-1.9.Q4_K_M.gguf \
  "https://huggingface.co/alekringtonnn-ai/zubr-mini-1.9-3b/resolve/main/zubr-mini-1.9.Q4_K_M.gguf"

The same links also work in a browser: open the file page and click "Download", or append ?download=true to the URL.

Method 5: LM Studio / Jan (no command line)

Install LM Studio or Jan.
In the search tab, type zubr-mini-1.9-3b (or paste the repository link).
Select a quantization and click Download.
Start chatting in the built-in chat.

Method 6: Docker

docker model run hf.co/alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M

🚀 How to Run

Via vLLM (API server)

pip install vllm
vllm serve "alekringtonnn-ai/zubr-mini-1.9-3b"

Once started, the model is available through an OpenAI-compatible API at http://localhost:8000/v1.

Via Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id="alekringtonnn-ai/zubr-mini-1.9-3b",
    filename="*Q4_K_M.gguf",  # Or any other quantization
    verbose=False,
)

response = llm.create_chat_completion(
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello! Write a short poem about a bison."},
    ]
)
print(response["choices"][0]["message"]["content"])

Via Ollama in Python

import ollama

response = ollama.chat(
    model="hf.co/alekringtonnn-ai/zubr-mini-1.9-3b:Q4_K_M",
    messages=[
        {"role": "user", "content": "Hello! Tell me about yourself."}
    ]
)
print(response["message"]["content"])

⚙️ Recommended Generation Parameters

Parameter	Value	Comment
`temperature`	0.7	A balance between creativity and accuracy
`max_tokens`	512–2048	Depends on the task
`top_p`	0.9	A standard value for instruct models
`num_ctx` (context)	4096+	Context window size; affects RAM usage

Downloads last month: 719

GGUF

Model size

3B params

Architecture

mistral3

Hardware compatibility

2-bit

3-bit

4-bit

6-bit

8-bit

Model tree for alekringtonnn-ai/zubr-mini-1.9-3b

Base model

mistralai/Ministral-3-3B-Base-2512

Quantized

mistralai/Ministral-3-3B-Instruct-2512

Quantized

mistralai/Ministral-3-3B-Instruct-2512-GGUF

Quantized

(2)

this model

Finetunes

1 model

🦬 Zubr Mini 1.9 3B

📖 What This Model Is

Key Features

Model Tree

📊 Versions (Quantizations) in the Repository

📥 How to Download

Requirements

Method 1: Ollama (the easiest)

Method 2: llama.cpp

Method 3: huggingface-cli (direct file downloads)

Method 4: Direct links (browser / wget / curl)

Method 5: LM Studio / Jan (no command line)

Method 6: Docker

🚀 How to Run

Via vLLM (API server)

Via Python (llama-cpp-python)

Via Ollama in Python

⚙️ Recommended Generation Parameters

Model tree for alekringtonnn-ai/zubr-mini-1.9-3b

Method 3: `huggingface-cli` (direct file downloads)