Instructions to use AtomicChat/gemma-4-E4B-it-assistant-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AtomicChat/gemma-4-E4B-it-assistant-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AtomicChat/gemma-4-E4B-it-assistant-GGUF",
	filename="gemma-4-E4B-it-assistant.F16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use AtomicChat/gemma-4-E4B-it-assistant-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AtomicChat/gemma-4-E4B-it-assistant-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AtomicChat/gemma-4-E4B-it-assistant-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AtomicChat/gemma-4-E4B-it-assistant-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AtomicChat/gemma-4-E4B-it-assistant-GGUF: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 AtomicChat/gemma-4-E4B-it-assistant-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AtomicChat/gemma-4-E4B-it-assistant-GGUF: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 AtomicChat/gemma-4-E4B-it-assistant-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AtomicChat/gemma-4-E4B-it-assistant-GGUF:Q4_K_M

Use Docker

docker model run hf.co/AtomicChat/gemma-4-E4B-it-assistant-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use AtomicChat/gemma-4-E4B-it-assistant-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AtomicChat/gemma-4-E4B-it-assistant-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AtomicChat/gemma-4-E4B-it-assistant-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AtomicChat/gemma-4-E4B-it-assistant-GGUF:Q4_K_M

Ollama
How to use AtomicChat/gemma-4-E4B-it-assistant-GGUF with Ollama:
```
ollama run hf.co/AtomicChat/gemma-4-E4B-it-assistant-GGUF:Q4_K_M
```

Unsloth Studio new

How to use AtomicChat/gemma-4-E4B-it-assistant-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 AtomicChat/gemma-4-E4B-it-assistant-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 AtomicChat/gemma-4-E4B-it-assistant-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AtomicChat/gemma-4-E4B-it-assistant-GGUF to start chatting

Docker Model Runner
How to use AtomicChat/gemma-4-E4B-it-assistant-GGUF with Docker Model Runner:
```
docker model run hf.co/AtomicChat/gemma-4-E4B-it-assistant-GGUF:Q4_K_M
```

Lemonade

How to use AtomicChat/gemma-4-E4B-it-assistant-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AtomicChat/gemma-4-E4B-it-assistant-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E4B-it-assistant-GGUF-Q4_K_M

List all available models

lemonade list

Not working

by bgeneto - opened 22 days ago

Discussion

bgeneto

22 days ago

It doesn't work for me, someone else had success with it. I'm using unsloth gemma-4-E4B-it-UD-Q4_K_XL.gguf and gemma-4-E4B-it-assistant.Q8_0.gguf. llama cpp called this way:

CUDA_VISIBLE_DEVICES=1 ./build/bin/llama-server \
    --model ~/models/gemma-4-E4B-it-UD-Q4_K_XL.gguf \
    --temp 1.0 \
    --top-p 0.95 \
    --top-k 64 \
    --ctx-size 65536 \
    --flash-attn on \
    --mtp-head ~/models/gemma-4-E4B-it-assistant.Q8_0.gguf \
    --spec-type mtp \
    --draft-block-size 2 --draft-max 8 --draft-min 0 \
    -ngl 99 -ngld 99 \
    -ctk q4_0 -ctv q4_0 -ctkd q4_0 -ctvd q4_0 \
    --batch-size 1024 \
    --ubatch-size 1024 \
    --parallel 1 \
    --threads 8 \
    --threads-batch 8 \
    --cache-ram -1 \
    --no-mmap \
    --jinja \
    --host 0.0.0.0 \
    --port 8002

But no single request works, getting this error:

/app/ggml/src/ggml.c:3665: GGML_ASSERT(ggml_nelements(a) == ne0*ne1*ne2) failed

hellork

19 days ago

•

edited 19 days ago

I had to export LD_LIBRARY_PATH=$(pwd) # run in your build/bin
And then it gets a little farther and the turbo3 quants start working.
Yet I find it is the --spect-type mtp that is still causing a crash.
And without it, there is no speedup over running just the model by itself...

The crash was caused by the RTX 3070's 860 flash attention heads
We're finding out more about this stuff every day.
Turboquant hasn't made flash attention templates for Ampere.
So it kills the server with an assertion.

It works by running the model with --flash-attn off
But then we're back at no speedup over running just the model by itself...
fattn.cu
146 case 512:
147 GGML_ASSERT(V->ne[0] == 512);
148 ggml_cuda_flash_attn_ext_mma_f16_switch_ncols2<512, 512>(ctx, dst);

This poem was brought to you by late night gdb session.

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