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"

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

#27

by btdeviant - opened Apr 12

Discussion

btdeviant

Apr 12

The updated chat template baked into the Apr 11 GGUF is dramatically slower to render in llama.cpp's Jinja engine, adding ~7.5 seconds of CPU-bound overhead per request on long conversations. KV cache and GPU prompt processing are not affected — the bottleneck is entirely in template rendering before inference begins.

Environment

llama.cpp b8757 (ghcr.io/ggml-org/llama.cpp:server-cuda, latest)
gemma-4-26B-A4B-it-BF16 on NVIDIA RTX PRO 6000 Blackwell
Server flags: -ngl 999 -np 1 --reasoning off
No --mmproj
Test payload: 633 messages (~6,113 tokens after template rendering)

Comparison: Old (Apr 7) vs New (Apr 11) GGUF

Both GGUFs produce identical token counts (~6,113 tokens from 633 messages). KV cache works correctly in both cases. The difference is purely in template rendering time.

Apr 7 GGUF (old template):

=== Cold request (633 messages) ===
real    0m2.231s          <-- total wall clock

=== Warm request (identical payload, cache hit) ===
real    0m0.225s          <-- cache works, 1 token processed

=== Server timing (cold) ===
prompt eval time =    2019.90 ms /  6113 tokens (0.33 ms per token, 3026.39 t/s)
total time       =    2019.90 ms /  6114 tokens

=== Server timing (warm) ===
prompt eval time =      16.88 ms /     1 tokens
total time       =      16.88 ms /     2 tokens

Wall clock (2.2s) ≈ server total time (2.0s). Minimal template overhead (~200ms).

Apr 11 GGUF (new template):

=== Cold request (633 messages) ===
real    0m9.535s          <-- total wall clock

=== Warm request (identical payload, cache hit) ===
real    0m7.486s          <-- cache hits but still 7.5s wall clock

=== Incremental request (634 messages) ===
real    0m8.178s

=== Server timing (cold) ===
prompt eval time =    1992.66 ms /  6114 tokens (GPU processing similar)
total time       =    1992.66 ms /  6114 tokens

=== Server timing (warm, 1 token from cache) ===
prompt eval time =      19.39 ms /     1 tokens
total time       =      19.39 ms /     2 tokens

Server total time is 2s (same as old), but wall clock is 7.5-9.5s. The **7.5 seconds** between wall clock and server timing is spent in Jinja template rendering before inference begins. This overhead is paid on every request regardless of KV cache state.

Server logs confirm KV cache is working (warm request):

slot update_slots: id  0 | task 6 | need to evaluate at least 1 token (n_past = 6113, task.n_tokens() = 6113)
slot update_slots: id  0 | task 6 | n_past was set to 6112
slot update_slots: id  0 | task 6 | prompt processing done, n_tokens = 6113, batch.n_tokens = 1

Root cause

The new template introduces more complex Jinja logic per message (reasoning content replay, <|channel>thought markers, as noted by https://github.com/asf0/gemma4_jinja/). llama.cpp's Jinja engine appears to scale poorly with this added complexity × message count: ~~12ms per message on the new template vs ~0.3ms per message on the old template (~~40x slower per message).

Impact

For multi-turn applications (voice assistants, agents with tool use), conversations grow to hundreds of messages quickly. At 633 messages:

Old template: 253ms warm, 2.2s cold — usable
New template: 7.5s warm, 9.5s cold — unusable

Workaround

Pinned to the Apr 7 GGUF. The <|channel>thought tag leakage from the old template can be stripped in application code.

https://github.com/ggml-org/llama.cpp/issues/21468 (Gemma 4 cache reuse issues)
https://github.com/asf0/gemma4_jinja/ (community template fix stripping the problematic sections)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

unsloth
/

gemma-4-26B-A4B-it-GGUF

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

Environment

Comparison: Old (Apr 7) vs New (Apr 11) GGUF

Root cause

Impact

Workaround

Related