Instructions to use timothywong731/tim-360m-base-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timothywong731/tim-360m-base-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="timothywong731/tim-360m-base-GGUF",
	filename="tim-360m-base.F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use timothywong731/tim-360m-base-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 timothywong731/tim-360m-base-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf timothywong731/tim-360m-base-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf timothywong731/tim-360m-base-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf timothywong731/tim-360m-base-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 timothywong731/tim-360m-base-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf timothywong731/tim-360m-base-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 timothywong731/tim-360m-base-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf timothywong731/tim-360m-base-GGUF:Q4_K_M

Use Docker

docker model run hf.co/timothywong731/tim-360m-base-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use timothywong731/tim-360m-base-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "timothywong731/tim-360m-base-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timothywong731/tim-360m-base-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/timothywong731/tim-360m-base-GGUF:Q4_K_M

Ollama
How to use timothywong731/tim-360m-base-GGUF with Ollama:
```
ollama run hf.co/timothywong731/tim-360m-base-GGUF:Q4_K_M
```

Unsloth Studio

How to use timothywong731/tim-360m-base-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 timothywong731/tim-360m-base-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 timothywong731/tim-360m-base-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for timothywong731/tim-360m-base-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use timothywong731/tim-360m-base-GGUF with Docker Model Runner:
```
docker model run hf.co/timothywong731/tim-360m-base-GGUF:Q4_K_M
```

Lemonade

How to use timothywong731/tim-360m-base-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull timothywong731/tim-360m-base-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.tim-360m-base-GGUF-Q4_K_M

List all available models

lemonade list

TIM-360M-base — GGUF

GGUF quantizations of TIM-360M-base for llama.cpp and downstream runtimes (Ollama, LM Studio, llamafile). This is the base model — a from-scratch 361.8M-parameter decoder-only transformer. It is not instruction-tuned; for chat use tim-360m-instruct.

Converted from the Qwen3ForCausalLM export (arch: qwen3, byte-level BPE, Llama-3-family pre-tokenizer).

Files

File	Quant	Size	Use when
`tim-360m-base.F16.gguf`	F16	692 MB	Reference / lossless; re-quantize from this
`tim-360m-base.Q8_0.gguf`	Q8_0	369 MB	Near-lossless, minimal quality loss
`tim-360m-base.Q4_K_M.gguf`	Q4_K_M	258 MB	Smallest; best size/quality trade-off for CPU

At this scale everything runs comfortably on CPU.

Usage

llama.cpp:

llama-cli -m tim-360m-base.Q4_K_M.gguf -p "The capital of France is" -n 64

Ollama (Modelfile):

FROM ./tim-360m-base.Q4_K_M.gguf

ollama create tim-360m-base -f Modelfile
ollama run tim-360m-base "The capital of France is"

This is a base completion model — give it a prefix to continue, not a chat prompt.

Provenance & license

Apache-2.0. See the source model card for architecture, training data, and evaluation. Pretraining data (all named, public): FineWeb-Edu (ODC-BY), DCLM-Baseline (CC-BY-4.0), Stack-Edu, FineMath (ODC-BY).

Downloads last month: -

GGUF

Model size

0.4B params

Architecture

qwen3

Hardware compatibility

4-bit

8-bit

16-bit

Model tree for timothywong731/tim-360m-base-GGUF

Base model

timothywong731/tim-360m-base

Quantized

(1)

this model