Instructions to use unsloth/gemma-4-26B-A4B-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/gemma-4-26B-A4B-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/gemma-4-26B-A4B-it-GGUF",
	filename="BF16/gemma-4-26B-A4B-it-BF16-00001-of-00002.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/gemma-4-26B-A4B-it-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 unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf unsloth/gemma-4-26B-A4B-it-GGUF:UD-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 unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf unsloth/gemma-4-26B-A4B-it-GGUF:UD-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 unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M

Use Docker

docker model run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M

LM Studio
Jan

vLLM

How to use unsloth/gemma-4-26B-A4B-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/gemma-4-26B-A4B-it-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": "unsloth/gemma-4-26B-A4B-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M

Ollama
How to use unsloth/gemma-4-26B-A4B-it-GGUF with Ollama:
```
ollama run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M
```

Unsloth Studio

How to use unsloth/gemma-4-26B-A4B-it-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 unsloth/gemma-4-26B-A4B-it-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 unsloth/gemma-4-26B-A4B-it-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/gemma-4-26B-A4B-it-GGUF to start chatting

How to use unsloth/gemma-4-26B-A4B-it-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/gemma-4-26B-A4B-it-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use unsloth/gemma-4-26B-A4B-it-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use unsloth/gemma-4-26B-A4B-it-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M
```

Lemonade

How to use unsloth/gemma-4-26B-A4B-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-26B-A4B-it-GGUF-UD-Q4_K_M

List all available models

lemonade list

New discussion

Resources

View closed (8)

Gemma 4 26B-A4B GGUF Benchmarks

pinned

👍🔥 12

#35 opened 3 months ago by

danielhanchen

Gemma 4 Tool Calling is amazing in Unsloth Studio!

pinned

🔥 5

#4 opened 4 months ago by

danielhanchen

Updated all with official Gemma chat template update

#45 opened 9 days ago by

danielhanchen

Gemma 4 26B A4B — MoE on mobile is the future

#44 opened 30 days ago by

3morixd

Chat template may re-inject prior-turn reasoning during multi-turn tool use → repetition loops

#43 opened about 2 months ago by

ManniX-ITA

Benchmarked this quant on BFCL v4: 89% non-live function-calling, fits 16GB with 65k context

#42 opened about 2 months ago by

tumbak

Gemma 4 MTP assistant/drafter models in GGUF

#41 opened 2 months ago by

redLiw

Insanely good 2-bit quant

👍 1

#40 opened 3 months ago by

cogitech

New Gemma chat template update by Google

👍 11

#39 opened 3 months ago by

danielhanchen

NVFP4 version

👍 6

#38 opened 3 months ago by

WhiskyAKM

gemma4

#37 opened 3 months ago by

willowoods

Tool call tokens use hybrid format incompatible with Ollama's PARSER gemma4

#36 opened 3 months ago by

kbryss

So what's the difference between the IQ4_XS and IQ4_NL quants?

#34 opened 3 months ago by

xwildfyre

Quant for non-Latin languages

#33 opened 3 months ago by

Theory-of-mind

How to set image budget?

#32 opened 3 months ago by

IlysvlVEizbr

[BUG] Vision capability not working for Gemma4 GGUF in Ollama

#31 opened 3 months ago by

notuncommon

Weird issue with closing </div>

#30 opened 3 months ago by

Fxvoid

Roleplay viability

🤝 1

#29 opened 3 months ago by

yano2mch

Chat template is busted

#28 opened 3 months ago by

FrenzyBiscuit

Apr 11 chat template causes ~7.5s template rendering overhead per request in llama.cpp

#27 opened 3 months ago by

btdeviant

llama.cpp flags / visual token budget

#26 opened 4 months ago by

234r89r23u89023rui90

D:\a\llama.cpp\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.cu:911: GGML_ASSERT(tensor->view_src == nullptr) failed

#25 opened 4 months ago by

osabc

Apr 11: Updated with Google chat template fixes + more

🚀❤️ 17

#24 opened 4 months ago by

danielhanchen

Do NOT use CUDA 13.2

❤️ 12

#22 opened 4 months ago by

danielhanchen

Gemma 4 seems to work best with high temperature for coding

👍 1

#21 opened 4 months ago by

Reverger

Apr 8 - New GGUF Updates

🚀❤️ 14

#20 opened 4 months ago by

danielhanchen

gguf updates

👀 5

#17 opened 4 months ago by

tstello

Ollama Error

👍 1

#16 opened 4 months ago by

edm-research

Inference speed on 12GB VRAM

#15 opened 4 months ago by

drakexp

Fails to run on vLLM

#14 opened 4 months ago by

Skodra

Only 2nd <13GB model to one-shot the Heptagon-Tumbler

🔥👍 4

#12 opened 4 months ago by

BingoBird

New uploads adds llama.cpp fixes

👍 6

#11 opened 4 months ago by

danielhanchen

Commit description

👍 4

#10 opened 4 months ago by

Kelheor

Q4_0 and Q4_1?

👍 2

#9 opened 4 months ago by

elpirater312

How to enable thinking

👍❤️ 10

#6 opened 4 months ago by

watchingyousleep

Tool call with dates fails

#5 opened 4 months ago by

EmilPi

Model produces `<|channel><unused49><unused49><unused49>`

👍 5

#2 opened 4 months ago by

kyuz0