Instructions to use david-ar/20q-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use david-ar/20q-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="david-ar/20q-GGUF",
	filename="twentyq-f16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use david-ar/20q-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf david-ar/20q-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf david-ar/20q-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf david-ar/20q-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf david-ar/20q-GGUF:F16

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 david-ar/20q-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf david-ar/20q-GGUF:F16

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 david-ar/20q-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf david-ar/20q-GGUF:F16

Use Docker

docker model run hf.co/david-ar/20q-GGUF:F16

LM Studio
Jan
Ollama
How to use david-ar/20q-GGUF with Ollama:
```
ollama run hf.co/david-ar/20q-GGUF:F16
```

Unsloth Studio new

How to use david-ar/20q-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 david-ar/20q-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 david-ar/20q-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for david-ar/20q-GGUF to start chatting

Docker Model Runner
How to use david-ar/20q-GGUF with Docker Model Runner:
```
docker model run hf.co/david-ar/20q-GGUF:F16
```

Lemonade

How to use david-ar/20q-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull david-ar/20q-GGUF:F16

Run and chat with the model

lemonade run user.20q-GGUF-F16

List all available models

lemonade list

TwentyQ — GGUF

GGUF quantized versions of david-ar/20q, the world's smallest chat model.

This model was natively trained at 2-bit precision. All quantization levels above Q2_K are technically upscaled. Q2_K is the model's native precision.

Available Quantizations

File	Quant	Size	Quality Loss
twentyq-f32.gguf	F32	762 KB	0%
twentyq-f16.gguf	F16	397 KB	0%
twentyq-q8_0.gguf	Q8_0	228 KB	0%
twentyq-q4_0.gguf	Q4_0	135 KB	0%
twentyq-q2_k.gguf	Q2_K	95 KB	0%

All quantizations are lossless because the original weights are 2-bit integers (values 0-3). Q2_K is the only quantization level that doesn't waste bits.

Architecture

general.architecture: twentyq
twentyq.block_count: 0
twentyq.embedding_length: 156
twentyq.attention.head_count: 156
twentyq.context_length: 20
twentyq.vocab_size: 1200

Zero transformer blocks. 156 attention heads. 20-token context window. The output projection layer (output.weight) contains the entire model.

Compatibility

These files require a runtime with twentyq architecture support, which does not currently exist in llama.cpp, ollama, or any other GGUF runtime. For inference, use the original model via the transformers library, or the live demo.

Downloads last month: 9

GGUF

Model size

187k params

Architecture

twentyq

Hardware compatibility

2-bit

4-bit

8-bit

16-bit

32-bit

Inference Providers NEW

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

Model tree for david-ar/20q-GGUF

Base model

david-ar/20q

Quantized

(1)

this model