t-tech/ T-lite-it-2.1

1,508 Downloads Updated 6 months ago

tools thinking

ollama run t-tech/T-lite-it-2.1:q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "t-tech/T-lite-it-2.1:q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='t-tech/T-lite-it-2.1:q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 't-tech/T-lite-it-2.1:q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model t-tech/T-lite-it-2.1:q4_K_M

Codex App

Codex App ollama launch codex-app --model t-tech/T-lite-it-2.1:q4_K_M

OpenClaw

OpenClaw ollama launch openclaw --model t-tech/T-lite-it-2.1:q4_K_M

Hermes Agent

Hermes Agent ollama launch hermes --model t-tech/T-lite-it-2.1:q4_K_M

Codex

Codex ollama launch codex --model t-tech/T-lite-it-2.1:q4_K_M

OpenCode

OpenCode ollama launch opencode --model t-tech/T-lite-it-2.1:q4_K_M

Models

Name

6 models

Size / Usage

Context

Input

T-lite-it-2.1:q4_K_M

5.0GB · 40K context window · Text · 6 months ago

T-lite-it-2.1:q4_K_M

5.0GB

40K

Text

T-lite-it-2.1:q5_0

5.7GB · 40K context window · Text · 6 months ago

T-lite-it-2.1:q5_0

5.7GB

40K

Text

T-lite-it-2.1:q5_K_S

5.7GB · 40K context window · Text · 6 months ago

T-lite-it-2.1:q5_K_S

5.7GB

40K

Text

T-lite-it-2.1:q5_K_M

5.9GB · 40K context window · Text · 6 months ago

T-lite-it-2.1:q5_K_M

5.9GB

40K

Text

T-lite-it-2.1:q6_K

6.7GB · 40K context window · Text · 6 months ago

T-lite-it-2.1:q6_K

6.7GB

40K

Text

T-lite-it-2.1:q8_0

8.7GB · 40K context window · Text · 6 months ago

T-lite-it-2.1:q8_0

8.7GB

40K

Text

Readme

T-lite-it-2.1

🚨 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.

Description

T-lite-it-2.1 is an efficient Russian model built upon the Qwen 3 architecture, featuring significant improvements in instruction following and adds support for tool-calling capabilities — a key advancement over T-lite-it-1.0, which lacks tool-use support. Outperforms Qwen3-8B in tool calling scenarios, which is essential for agentic applications. Built for both general tasks and complex workflows, with higher Russian text generation throughput enabled by optimized tokenizer.

More info available here: https://huggingface.co/t-tech/T-lite-it-2.1

Available quantisations

All available quantisations are presented here: https://ollama.com/t-tech/T-lite-it-2.1/tags

Quickstart

ollama run t-tech/T-lite-it-2.1:q4_K_M

# T-lite-it-2.1

**🚨 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.**

## Description
[T-lite-it-2.1](https://huggingface.co/t-tech/T-lite-it-2.1) is an efficient Russian model built upon the Qwen 3 architecture, featuring significant improvements in instruction following and **adds support for tool-calling capabilities** — a key advancement over [T-lite-it-1.0](https://huggingface.co/t-tech/T-lite-it-1.0), which lacks tool-use support.
Outperforms Qwen3-8B in tool calling scenarios, which is essential for agentic applications. Built for both general tasks and complex workflows, with higher Russian text generation throughput enabled by optimized tokenizer.

More info available here: https://huggingface.co/t-tech/T-lite-it-2.1

## Available quantisations

All available quantisations are presented here: https://ollama.com/t-tech/T-lite-it-2.1/tags

## Quickstart

```shell
ollama run t-tech/T-lite-it-2.1:q4_K_M
```

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)