Instructions to use Sumitc13/sarvam-30b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sumitc13/sarvam-30b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Sumitc13/sarvam-30b-GGUF",
	filename="sarvam-30B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Sumitc13/sarvam-30b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Sumitc13/sarvam-30b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Sumitc13/sarvam-30b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Sumitc13/sarvam-30b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Sumitc13/sarvam-30b-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 Sumitc13/sarvam-30b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Sumitc13/sarvam-30b-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 Sumitc13/sarvam-30b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Sumitc13/sarvam-30b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Sumitc13/sarvam-30b-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use Sumitc13/sarvam-30b-GGUF with Ollama:
```
ollama run hf.co/Sumitc13/sarvam-30b-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Sumitc13/sarvam-30b-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 Sumitc13/sarvam-30b-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 Sumitc13/sarvam-30b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Sumitc13/sarvam-30b-GGUF to start chatting

Pi new

How to use Sumitc13/sarvam-30b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Sumitc13/sarvam-30b-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": "Sumitc13/sarvam-30b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Sumitc13/sarvam-30b-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Sumitc13/sarvam-30b-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 Sumitc13/sarvam-30b-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Sumitc13/sarvam-30b-GGUF with Docker Model Runner:
```
docker model run hf.co/Sumitc13/sarvam-30b-GGUF:Q4_K_M
```

Lemonade

How to use Sumitc13/sarvam-30b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Sumitc13/sarvam-30b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.sarvam-30b-GGUF-Q4_K_M

List all available models

lemonade list

sarvam-30b-GGUF

GGUF quantizations of sarvamai/sarvam-30b for use with llama.cpp.

Compatibility: These GGUFs use the bailingmoe2 architecture. Make sure you're on a recent version of llama.cpp (or any tool that bundles llama.cpp like LM Studio / Ollama / koboldcpp) for full tokenizer support across English + 22 Indian languages.

Available Quantizations

File	Quant	Size	BPW	Description
`sarvam-30B-full-BF16.gguf`	BF16	~64 GB	16.00	Full precision, no quantization
`sarvam-30B-Q8_0.gguf`	Q8_0	~34 GB	8.50	Highest quality quantization
`sarvam-30B-Q6_K.gguf`	Q6_K	~26 GB	6.57	Great quality, fits in 32GB VRAM
`sarvam-30B-Q4_K_M.gguf`	Q4_K_M	~19 GB	4.87	Good balance of quality and size

Model Details

Architecture: SarvamMoEForCausalLM — converted as bailingmoe2 (the architectures are equivalent; Sarvam uses full rotary and zero-mean normalized expert bias, handled at conversion time)
Parameters: ~30B total
Layers: 19 (1 dense FFN + 18 MoE)
Experts: 128 routed (top-6 routing) + 1 shared expert
Gating: Sigmoid with zero-mean normalized expert bias, routed_scaling_factor=2.5
Attention: GQA with 64 heads, 4 KV heads, head_dim=64, combined QKV with QK RMSNorm
Activation: SwiGLU
Normalization: RMSNorm (eps=1e-6)
Vocab size: 262,144
Context length: up to 131,072 (model trained context); chat templates use 16,384 by default
RoPE theta: 8,000,000
Tokenizer: SentencePiece-style BPE, supports English + 22 Indian languages with byte fallback

Tokenizer parity

Verified 50/50 probes match Hugging Face reference tokenizer exactly across: English, Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia, Assamese, Urdu, Sindhi, Nepali, Sanskrit, Maithili, Konkani, Manipuri, Bodo, Santali, Kashmiri, Dogri, plus mixed-script and edge-case probes.

Usage

# Interactive chat
llama-cli -m sarvam-30B-Q6_K.gguf -p "Hello, how are you?" -n 512 -ngl 99

# Server mode (use --jinja for the embedded chat template)
llama-server -m sarvam-30B-Q6_K.gguf -ngl 99 -c 16384 --jinja

Thinking mode

The model supports enable_thinking via the chat template. When using llama-server --jinja:

curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
  "messages": [{"role": "user", "content": "What is 25 * 37?"}],
  "max_tokens": 1024,
  "chat_template_kwargs": {"enable_thinking": true}
}'

Note: enable_thinking=false adds the <|nothink|> token but the base model may still emit <think>...</think> (upstream model issue, see sarvamai/sarvam-30b#11). reasoning_effort is not in the public chat template and is silently ignored.

VRAM Requirements

Quant	Full GPU Offload	Partial Offload (24GB)
Q4_K_M	~19 GB	All layers on GPU
Q6_K	~26 GB	All layers on GPU (32GB cards)
Q8_0	~34 GB	~70% layers on GPU (32GB cards)
BF16	~64 GB	~50% layers on GPU (32GB cards)

Tested On

NVIDIA RTX 5090 (32GB VRAM), CUDA 13.0
All quantizations produce coherent output across English and Indian languages
Q6_K runs at ~305 tokens/sec generation speed

Credits

Original model by Sarvam AI
Quantized by Sumitc13
Architecture reuses bailingmoe2 already in llama.cpp (PR #20275 adds the Sarvam-specific tokenizer)

Downloads last month: 1,561

GGUF

Model size

32B params

Architecture

bailingmoe2

Hardware compatibility

4-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Sumitc13/sarvam-30b-GGUF

Base model

sarvamai/sarvam-30b

Quantized

(20)

this model