Instructions to use TheREZOR/TinyTalk-2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheREZOR/TinyTalk-2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheREZOR/TinyTalk-2-GGUF",
	filename="TinyTalk-2-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TheREZOR/TinyTalk-2-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 TheREZOR/TinyTalk-2-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf TheREZOR/TinyTalk-2-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheREZOR/TinyTalk-2-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf TheREZOR/TinyTalk-2-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 TheREZOR/TinyTalk-2-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf TheREZOR/TinyTalk-2-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 TheREZOR/TinyTalk-2-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheREZOR/TinyTalk-2-GGUF:Q8_0

Use Docker

docker model run hf.co/TheREZOR/TinyTalk-2-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use TheREZOR/TinyTalk-2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheREZOR/TinyTalk-2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheREZOR/TinyTalk-2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheREZOR/TinyTalk-2-GGUF:Q8_0

Ollama
How to use TheREZOR/TinyTalk-2-GGUF with Ollama:
```
ollama run hf.co/TheREZOR/TinyTalk-2-GGUF:Q8_0
```

Unsloth Studio

How to use TheREZOR/TinyTalk-2-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 TheREZOR/TinyTalk-2-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 TheREZOR/TinyTalk-2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheREZOR/TinyTalk-2-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use TheREZOR/TinyTalk-2-GGUF with Docker Model Runner:
```
docker model run hf.co/TheREZOR/TinyTalk-2-GGUF:Q8_0
```

Lemonade

How to use TheREZOR/TinyTalk-2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheREZOR/TinyTalk-2-GGUF:Q8_0

Run and chat with the model

lemonade run user.TinyTalk-2-GGUF-Q8_0

List all available models

lemonade list

TinyTalk 2 — GGUF

GGUF builds of TheREZOR/TinyTalk-2, an 8M-parameter chatbot originally built to run on an ESP32-S3 microcontroller (cardputer-ai firmware).

Run with Ollama

ollama run hf.co/TheREZOR/TinyTalk-2-GGUF

Run with llama.cpp

llama-cli -m TinyTalk-2-f16.gguf -p "User: what sound does a dog make?\nBot:" \
  --temp 0.8 --top-p 0.9 -n 40 -r "<|endoftext|>"

Files

File	Bytes/weight	Size	Note
`TinyTalk-2-f16.gguf`	f16	39 MB	recommended — tiny models lose quality fast below f16
`TinyTalk-2-Q8_0.gguf`	q8_0	21 MB	fine in practice

Architecture note (why this says "gpt2")

The original model is GPT-Neo, which llama.cpp does not support. These GGUFs are a mathematically exact GPT-2 conversion (verified: max logit delta 2.6e-05, identical greedy decodes): GPT-Neo's missing 1/sqrt(head_dim) attention scaling is baked into the q-projection weights, and at the model's 256-token context the alternating local attention (window 256) is identical to global attention. Conversion script: tools/export_gpt2.py.

Prompt format

User: <message>
Bot: <reply><|endoftext|>

Story mode: Summary: <what the story is about>\nStory: The chat template is embedded in the GGUF metadata; <|endoftext|> is the stop token. Context length: 256.

License

CC BY-NC-SA 4.0 (non-commercial) — see the main model card for full dataset attribution.

Downloads last month: 169

GGUF

Model size

19.2M params

Architecture

gpt2

Hardware compatibility

8-bit

16-bit

Model tree for TheREZOR/TinyTalk-2-GGUF

Base model

roneneldan/TinyStories-Instruct-8M

Finetuned

TheREZOR/TinyTalk-2

Quantized

(1)

this model