Instructions to use mashriram/Sarvam-1-VL-4B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mashriram/Sarvam-1-VL-4B-Instruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mashriram/Sarvam-1-VL-4B-Instruct-GGUF",
	filename="qwen3-vl-4b-instruct.BF16-mmproj.gguf",
)

llm.create_chat_completion(
	messages = "\"Меня зовут Вольфганг и я живу в Берлине\""
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mashriram/Sarvam-1-VL-4B-Instruct-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 mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16

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 mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16

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 mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16

Use Docker

docker model run hf.co/mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16

LM Studio
Jan
Ollama
How to use mashriram/Sarvam-1-VL-4B-Instruct-GGUF with Ollama:
```
ollama run hf.co/mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16
```

Unsloth Studio

How to use mashriram/Sarvam-1-VL-4B-Instruct-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 mashriram/Sarvam-1-VL-4B-Instruct-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 mashriram/Sarvam-1-VL-4B-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mashriram/Sarvam-1-VL-4B-Instruct-GGUF to start chatting

How to use mashriram/Sarvam-1-VL-4B-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16

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": "mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mashriram/Sarvam-1-VL-4B-Instruct-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 mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16

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 mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use mashriram/Sarvam-1-VL-4B-Instruct-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16

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 "mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16" \
  --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 mashriram/Sarvam-1-VL-4B-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16
```

Lemonade

How to use mashriram/Sarvam-1-VL-4B-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mashriram/Sarvam-1-VL-4B-Instruct-GGUF:BF16

Run and chat with the model

lemonade run user.Sarvam-1-VL-4B-Instruct-GGUF-BF16

List all available models

lemonade list

Sarvam-1-VL-4B-Instruct - GGUF (Quantized)

Model Description

GGUF quantized version for CPU/edge deployment using llama.cpp. Includes Q4_K_M quantization for optimal size/quality balance.

Files

qwen3-vl-4b-instruct.Q4_K_M.gguf - Quantized model (4-bit)
qwen3-vl-4b-instruct.BF16-mmproj.gguf - Quantized model (4-bit)

Training Details

Base Model: Qwen/Qwen3-VL-4B-Instruct
Quantization: Q4_K_M
Original Training: 2,000 steps, loss 6.25

Datasets

Trained on 4 datasets covering:

Translation (40%): BPCC - 22 Indic languages ↔ English
Instruction Following (20%): Pralekha - 11 language pairs
Document Layout (30%): IndicDLP - Document understanding
Visual QA (10%): DocVQA - Question answering

Supported Languages

Assamese, Bengali, Bodo, Dogri, Gujarati, Hindi, Kannada, Kashmiri, Konkani, Maithili, Malayalam, Marathi, Manipuri, Nepali, Odia, Punjabi, Sanskrit, Santali, Sindhi, Tamil, Telugu, Urdu, English

Usage with llama.cpp

# Run inference
llama-mtmd-cli \
  -m qwen3-vl-4b-instruct.Q4_K_M.gguf \
  --mmproj qwen3-vl-4b-instruct.BF16-mmproj.gguf \
  -p "Translate this to Hindi:" \
  --image document.jpg

Memory Requirements

Q4_K_M: ~2.5GB RAM
With mmproj: ~3GB RAM total

Performance

Speed: Fast CPU inference
Quality: Minimal degradation vs fp16
Deployment: Ideal for edge devices

License

Apache 2.0

Downloads last month: 31

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for mashriram/Sarvam-1-VL-4B-Instruct-GGUF

Base model

Qwen/Qwen3-VL-4B-Instruct

Quantized

(95)

this model

mashriram
/

Sarvam-1-VL-4B-Instruct-GGUF

Sarvam-1-VL-4B-Instruct - GGUF (Quantized)

Model Description

Files

Training Details

Datasets

Supported Languages

Usage with llama.cpp

Memory Requirements

Performance

License

Model tree for mashriram/Sarvam-1-VL-4B-Instruct-GGUF

Datasets used to train mashriram/Sarvam-1-VL-4B-Instruct-GGUF