Instructions to use RiosWesley/gemma-3-270M-Model-Router with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RiosWesley/gemma-3-270M-Model-Router with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RiosWesley/gemma-3-270M-Model-Router",
	filename="gemma-3-270m-it.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "\"I like you. I love you\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use RiosWesley/gemma-3-270M-Model-Router with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RiosWesley/gemma-3-270M-Model-Router:Q8_0
# Run inference directly in the terminal:
llama-cli -hf RiosWesley/gemma-3-270M-Model-Router:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RiosWesley/gemma-3-270M-Model-Router:Q8_0
# Run inference directly in the terminal:
llama-cli -hf RiosWesley/gemma-3-270M-Model-Router: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 RiosWesley/gemma-3-270M-Model-Router:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf RiosWesley/gemma-3-270M-Model-Router: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 RiosWesley/gemma-3-270M-Model-Router:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RiosWesley/gemma-3-270M-Model-Router:Q8_0

Use Docker

docker model run hf.co/RiosWesley/gemma-3-270M-Model-Router:Q8_0

LM Studio
Jan
Ollama
How to use RiosWesley/gemma-3-270M-Model-Router with Ollama:
```
ollama run hf.co/RiosWesley/gemma-3-270M-Model-Router:Q8_0
```

Unsloth Studio new

How to use RiosWesley/gemma-3-270M-Model-Router 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 RiosWesley/gemma-3-270M-Model-Router 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 RiosWesley/gemma-3-270M-Model-Router to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RiosWesley/gemma-3-270M-Model-Router to start chatting

Docker Model Runner
How to use RiosWesley/gemma-3-270M-Model-Router with Docker Model Runner:
```
docker model run hf.co/RiosWesley/gemma-3-270M-Model-Router:Q8_0
```

Lemonade

How to use RiosWesley/gemma-3-270M-Model-Router with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RiosWesley/gemma-3-270M-Model-Router:Q8_0

Run and chat with the model

lemonade run user.gemma-3-270M-Model-Router-Q8_0

List all available models

lemonade list

RiosWesley commited on Nov 20, 2025

Commit

ea8bc0a

verified ·

1 Parent(s): 683cb73

Trained with Unsloth - Ollama Modelfile

Browse files

Files changed (1) hide show

Modelfile +22 -0

Modelfile ADDED Viewed

	@@ -0,0 +1,22 @@

+FROM gemma-3-270m-it.Q8_0.gguf
+TEMPLATE """{{- $systemPromptAdded := false }}
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 }}
+{{- if eq .Role "user" }}<start_of_turn>user
+{{- if (and (not $systemPromptAdded) $.System) }}
+{{- $systemPromptAdded = true }}
+{{ $.System }}
+{{ end }}
+{{ .Content }}<end_of_turn>
+{{ if $last }}<start_of_turn>model
+{{ end }}
+{{- else if eq .Role "assistant" }}<start_of_turn>model
+{{ .Content }}{{ if not $last }}<end_of_turn>
+{{ end }}
+{{- end }}
+{{- end }}
+"""
+PARAMETER stop "<end_of_turn>"
+PARAMETER top_k 64
+PARAMETER top_p 0.95