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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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 Desktop

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 @earendil-works/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

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

Hermes Agent

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

OpenClaw

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"

danielhanchen commited on Jun 9

Commit

3d7a4fb

verified ·

1 Parent(s): 0a3dba9

Add root-level mtp- drafter for -hf auto-discovery; rename MTP/ drafters to mtp- prefix; update MTP README

Browse files

Files changed (6) hide show

.gitattributes +4 -0
MTP/README.md +24 -10
MTP/mtp-gemma-4-26B-A4B-it-BF16.gguf +3 -0
MTP/mtp-gemma-4-26B-A4B-it-F16.gguf +3 -0
MTP/mtp-gemma-4-26B-A4B-it-Q8_0.gguf +3 -0
mtp-gemma-4-26B-A4B-it-Q8_0.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -67,3 +67,7 @@ gemma-4-26B-A4B-it-UD-Q4_K_S_XS.gguf filter=lfs diff=lfs merge=lfs -text
 MTP/gemma-4-26B-A4B-it-MTP-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 MTP/gemma-4-26B-A4B-it-MTP-BF16.gguf filter=lfs diff=lfs merge=lfs -text
 MTP/gemma-4-26B-A4B-it-MTP-F16.gguf filter=lfs diff=lfs merge=lfs -text

 MTP/gemma-4-26B-A4B-it-MTP-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 MTP/gemma-4-26B-A4B-it-MTP-BF16.gguf filter=lfs diff=lfs merge=lfs -text
 MTP/gemma-4-26B-A4B-it-MTP-F16.gguf filter=lfs diff=lfs merge=lfs -text
+mtp-gemma-4-26B-A4B-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+MTP/mtp-gemma-4-26B-A4B-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+MTP/mtp-gemma-4-26B-A4B-it-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+MTP/mtp-gemma-4-26B-A4B-it-F16.gguf filter=lfs diff=lfs merge=lfs -text

MTP/README.md CHANGED Viewed

@@ -8,9 +8,11 @@ MTP was merged into llama.cpp on 2026-06-07 (PR ggml-org/llama.cpp#23398). You n
 ## Files
-- `gemma-4-26B-A4B-it-MTP-Q8_0.gguf` (smallest, recommended)
-- `gemma-4-26B-A4B-it-MTP-BF16.gguf`
-- `gemma-4-26B-A4B-it-MTP-F16.gguf`
 ## Build llama.cpp
@@ -23,20 +25,32 @@ cmake -B build -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=90
 cmake --build build --config Release -j --target llama-server
 ```
-## Run
 ```bash
-# grab the main model (any quant) and one drafter
 hf download unsloth/gemma-4-26B-A4B-it-GGUF gemma-4-26B-A4B-it-UD-Q4_K_M.gguf --local-dir .
-hf download unsloth/gemma-4-26B-A4B-it-GGUF MTP/gemma-4-26B-A4B-it-MTP-Q8_0.gguf --local-dir .
 ./build/bin/llama-server \
   -m gemma-4-26B-A4B-it-UD-Q4_K_M.gguf \
-  --model-draft MTP/gemma-4-26B-A4B-it-MTP-Q8_0.gguf \
   --spec-type draft-mtp --spec-draft-n-max 4 \
   -ngl 999 -fa on
 ```
-Multi GPU: add `--spec-draft-device CUDA0 -sm layer`.
-The drafter pairs with any quant of the 26B-A4B. Quantized KV cache works.

 ## Files
+A `mtp-` prefixed Q8_0 copy sits at the repo root so `-hf` can auto-discover it. All three precisions live in `MTP/`:
+- `mtp-gemma-4-26B-A4B-it-Q8_0.gguf` (smallest, recommended; same file is mirrored at the repo root)
+- `mtp-gemma-4-26B-A4B-it-BF16.gguf`
+- `mtp-gemma-4-26B-A4B-it-F16.gguf`
 ## Build llama.cpp
 cmake --build build --config Release -j --target llama-server
 ```
+## Run, the easy way
+A recent llama.cpp finds the drafter automatically from the root `mtp-` file, so `-hf` is all you need. No `--model-draft`.
+```bash
+./build/bin/llama-server \
+  -hf unsloth/gemma-4-26B-A4B-it-GGUF:UD-Q4_K_M \
+  --spec-type draft-mtp --spec-draft-n-max 4 \
+  -ngl 999 -fa on
+```
+If your build is too old to auto-discover the sibling, use the explicit form below.
+## Run with an explicit drafter
+Use this to choose a precision or point at a local file.
 ```bash
 hf download unsloth/gemma-4-26B-A4B-it-GGUF gemma-4-26B-A4B-it-UD-Q4_K_M.gguf --local-dir .
+hf download unsloth/gemma-4-26B-A4B-it-GGUF MTP/mtp-gemma-4-26B-A4B-it-Q8_0.gguf --local-dir .
 ./build/bin/llama-server \
   -m gemma-4-26B-A4B-it-UD-Q4_K_M.gguf \
+  --model-draft MTP/mtp-gemma-4-26B-A4B-it-Q8_0.gguf \
   --spec-type draft-mtp --spec-draft-n-max 4 \
   -ngl 999 -fa on
 ```
+Multi GPU: add `--spec-draft-device CUDA0 -sm layer`. The drafter pairs with any quant of the 26B-A4B. Quantized KV cache works.

MTP/mtp-gemma-4-26B-A4B-it-BF16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:01cdef467d12d51474b821542eb113cd8ac6ac3649b2a9f5f0a6f3a2eacd59a0
+size 855228576

MTP/mtp-gemma-4-26B-A4B-it-F16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:36bf2f6710cf06ff1a5d026cca49ba88bd3451d8588a484ca5a79c5e30aa45f2
+size 855228576

MTP/mtp-gemma-4-26B-A4B-it-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6326fb9f5e487aa8dcdd313a091e3c67724cb2a666ec3b7d2895b5b26d93ed1b
+size 461766816

mtp-gemma-4-26B-A4B-it-Q8_0.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6326fb9f5e487aa8dcdd313a091e3c67724cb2a666ec3b7d2895b5b26d93ed1b
+size 461766816