Instructions to use bubblspace/Timecapsule2.7B-g3n-mix-match-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bubblspace/Timecapsule2.7B-g3n-mix-match-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bubblspace/Timecapsule2.7B-g3n-mix-match-gguf",
	filename="tc_mixmatch_f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use bubblspace/Timecapsule2.7B-g3n-mix-match-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bubblspace/Timecapsule2.7B-g3n-mix-match-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf bubblspace/Timecapsule2.7B-g3n-mix-match-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bubblspace/Timecapsule2.7B-g3n-mix-match-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf bubblspace/Timecapsule2.7B-g3n-mix-match-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 bubblspace/Timecapsule2.7B-g3n-mix-match-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf bubblspace/Timecapsule2.7B-g3n-mix-match-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 bubblspace/Timecapsule2.7B-g3n-mix-match-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bubblspace/Timecapsule2.7B-g3n-mix-match-gguf:F16

Use Docker

docker model run hf.co/bubblspace/Timecapsule2.7B-g3n-mix-match-gguf:F16

LM Studio
Jan
Ollama
How to use bubblspace/Timecapsule2.7B-g3n-mix-match-gguf with Ollama:
```
ollama run hf.co/bubblspace/Timecapsule2.7B-g3n-mix-match-gguf:F16
```

Unsloth Studio new

How to use bubblspace/Timecapsule2.7B-g3n-mix-match-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 bubblspace/Timecapsule2.7B-g3n-mix-match-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 bubblspace/Timecapsule2.7B-g3n-mix-match-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bubblspace/Timecapsule2.7B-g3n-mix-match-gguf to start chatting

Docker Model Runner
How to use bubblspace/Timecapsule2.7B-g3n-mix-match-gguf with Docker Model Runner:
```
docker model run hf.co/bubblspace/Timecapsule2.7B-g3n-mix-match-gguf:F16
```

Lemonade

How to use bubblspace/Timecapsule2.7B-g3n-mix-match-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bubblspace/Timecapsule2.7B-g3n-mix-match-gguf:F16

Run and chat with the model

lemonade run user.Timecapsule2.7B-g3n-mix-match-gguf-F16

List all available models

lemonade list

TimeCapsule Gemma 3n 2.7B Slice (FP16 GGUF)

This model is a 2.7 B parameter sub‑model of Gemma 3n, created using the MatFormer (Matryoshka Transformer) architecture and the Mix‑n‑Match slicing approach. It was sliced from the E4B checkpoint using the official E2.69B (layer‑level) configuration.

🧠 Intended Use

Primary use: High‑precision inference with Ollama via FP16 GGUF.
Best suited for: TimeCapsule‑SLM deep‑research workflows where latency, accuracy, and compute tradeoffs matter.

⚠️ Limitations & Considerations

Derived from a larger model — may not match the full E4B model in some evaluations.
Operates in FP16 precision — requires hardware (like A100/GPU or Ollama host) with FP16 support.
No additional quantization applied, preserving accuracy at some memory cost.

🛠 Creation Details

Parent model: google/gemma-3n-E4B-it
Slice configuration: Config for E2.69B (layer-level) from the official slicing-configs dataset
Converted from .safetensors to FP16 GGUF using llama.cpp’s convert_hf_to_gguf.py
Uploaded to this repository as: tc_mixmatch_f16.gguf

🧪 Usage Example

ollama run hf.co/bubblspace/Timecapsule2.7B-g3n-mix-match-gguf

Downloads last month: 36

GGUF

Model size

6B params

Architecture

gemma3n

Hardware compatibility

16-bit

Inference Providers NEW

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

Model tree for bubblspace/Timecapsule2.7B-g3n-mix-match-gguf

Base model

google/gemma-3n-E4B

Finetuned

google/gemma-3n-E4B-it

Quantized

(67)

this model