Instructions to use matrixportalx/gemma-4-E4B-it-assistant-MTP-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 matrixportalx/gemma-4-E4B-it-assistant-MTP-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 matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_0
# Run inference directly in the terminal:
llama cli -hf matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_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 matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_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 matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_0

Use Docker

docker model run hf.co/matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_0

LM Studio
Jan
Ollama
How to use matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF with Ollama:
```
ollama run hf.co/matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_0
```

Unsloth Studio

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

Using HuggingFace Spaces for Unsloth

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

Atomic Chat new
Docker Model Runner
How to use matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_0
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull matrixportalx/gemma-4-E4B-it-assistant-MTP-GGUF:Q4_0

Run and chat with the model

lemonade run user.gemma-4-E4B-it-assistant-MTP-GGUF-Q4_0

List all available models

lemonade list

matrixportalx commited on 14 days ago

Commit

0132a0a

verified ·

1 Parent(s): ba6ffaf

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +31 -0

README.md ADDED Viewed

	@@ -0,0 +1,31 @@

+---
+license: gemma
+base_model: google/gemma-4-E4B-it-assistant
+tags:
+  - gguf
+  - llama.cpp
+  - gemma4
+  - mtp
+  - speculative-decoding
+library_name: gguf
+---
+# Gemma 4 E4B — MTP (assistant) head · GGUF
+`google/gemma-4-E4B-it-assistant` (Gemma 4 MTP / `gemma4-assistant` kafası)
+modelinin llama.cpp GGUF dönüşümleri. Bu dosyalar **ayrı MTP kafasıdır**
+(spekülatif üretim / draft-mtp) — tek başına sohbet modeli değildir; bir
+gemma4 E4B ana modeliyle birlikte kullanılır.
+## Dosyalar
+| Dosya | Tip |
+|-------|-----|
+| `gemma-4-E4B-it-assistant-f16.gguf` | F16 |
+| `gemma-4-E4B-it-assistant-Q4_0.gguf` | Q4_0 |
+| `gemma-4-E4B-it-assistant-Q6_K.gguf` | Q6_K |
+| `gemma-4-E4B-it-assistant-Q8_0.gguf` | Q8_0 |
+## Not
+Kafanın parametrelerinin büyük kısmı token gömmesindedir; daha düşük bitlerde
+(Q4_0) MTP kabul oranı bir miktar düşebilir. Kabul oranı en yüksek sürüm F16'dır.
+Dönüşüm llama.cpp commit `f955e39` ile yapılmıştır.