Instructions to use Timegravity/tamil-lm-2b-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 Timegravity/tamil-lm-2b-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 Timegravity/tamil-lm-2b-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf Timegravity/tamil-lm-2b-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Timegravity/tamil-lm-2b-gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf Timegravity/tamil-lm-2b-gguf:Q8_0

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 Timegravity/tamil-lm-2b-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Timegravity/tamil-lm-2b-gguf:Q8_0

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 Timegravity/tamil-lm-2b-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Timegravity/tamil-lm-2b-gguf:Q8_0

Use Docker

docker model run hf.co/Timegravity/tamil-lm-2b-gguf:Q8_0

LM Studio
Jan
Ollama
How to use Timegravity/tamil-lm-2b-gguf with Ollama:
```
ollama run hf.co/Timegravity/tamil-lm-2b-gguf:Q8_0
```
Unsloth Desktop

How to use Timegravity/tamil-lm-2b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Timegravity/tamil-lm-2b-gguf:Q8_0

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": "Timegravity/tamil-lm-2b-gguf:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Timegravity/tamil-lm-2b-gguf with Docker Model Runner:
```
docker model run hf.co/Timegravity/tamil-lm-2b-gguf:Q8_0
```

Lemonade

How to use Timegravity/tamil-lm-2b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Timegravity/tamil-lm-2b-gguf:Q8_0

Run and chat with the model

lemonade run user.tamil-lm-2b-gguf-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Timegravity/tamil-lm-2b-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 Timegravity/tamil-lm-2b-gguf:Q8_0

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 Timegravity/tamil-lm-2b-gguf:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Timegravity/tamil-lm-2b-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Timegravity/tamil-lm-2b-gguf:Q8_0

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 "Timegravity/tamil-lm-2b-gguf:Q8_0" \
  --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"

Timegravity/tamil-lm-2b-gguf

Quantised files and knowledge packs used by the Timegravity Tamil Android app, by Timegravity Labs Private Limited (Coimbatore, India). Model card of the weights: https://huggingface.co/Timegravity/tamil-lm-2b-instruct

Files

tamil-lm-2b-instruct-Q4_K_M.gguf: tamil-lm-2b-instruct round 4c, Q4_K_M, converted with the pinned llama.cpp.
qwen3.5/Qwen3.5-2B-Q4_K_M.gguf, qwen3.5/Qwen3.5-4B-Q4_K_M.gguf: Qwen 3.5 2B and 4B, Q4_K_M, converted with the pinned llama.cpp; licence in qwen3.5/LICENSE.
mmproj/tamil-lm-2b-instruct-mmproj-q8_0.gguf: vision projector for the Qwen 3.5 2B vision path.
packs/: knowledge packs (SQLite FTS5); licences and sources in packs/LICENSES.md.

GGUF files

Each GGUF file inherits the licence of its source weights:

tamil-lm-2b-instruct and tamil-lm-2b-base GGUF files: Apache License 2.0 (source weights Timegravity/tamil-lm-2b-instruct and -base, built on Qwen/Qwen3.5-2B-Base, Apache 2.0).
Qwen 3.5 2B and 4B GGUF conversions: Apache License 2.0, Copyright 2026 Alibaba Cloud (Qwen/Qwen3.5-2B, Qwen/Qwen3.5-4B).
Vision projector (mmproj): from Qwen/Qwen3.5-2B, Apache License 2.0.

Knowledge packs (packs/)

The pack files used by the Timegravity Tamil app are published here because their contents are adapted from CC BY-SA 4.0 sources and share-alike requires them to be redistributable under the same licence. The pack contents are licensed under Creative Commons Attribution-ShareAlike 4.0 International; each passage carries its source article title and URL, which is the attribution. Changes made: articles split into passages, markup and boilerplate removed, passages failing the family-safe filter dropped.

Sources: Tamil and English Wikipedia, Tamil and English Wikibooks, Tamil and English Wiktionary (contributors of each wiki).
The agriculture pack also holds entries from Tamil University's அறிவியல் களஞ்சியம் and வாழ்வியற் களஞ்சியம் on Tamil Wikisource, included under CC BY-SA on the strength of the Tamil Nadu Tamil Development Department order cited on their Wikimedia Commons file pages; the Commons licence review is pending (checked 2026-09-14) and the entries are removed if it fails.
The finance pack also contains 26 passages from epfo.gov.in reproduced under the EPFO copyright policy (reproduction permitted, accurately and with the source acknowledged); those passages are not relicensed under CC BY-SA.
The CC BY-SA licence covers the pack contents only. The Timegravity Tamil app that reads these files is proprietary and is not licensed under CC BY-SA.

Downloads last month: 102

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

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