Instructions to use itzune/morpheus-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use itzune/morpheus-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="itzune/morpheus-gguf",
	filename="morpheus-v2-mamba.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use itzune/morpheus-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 itzune/morpheus-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf itzune/morpheus-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf itzune/morpheus-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf itzune/morpheus-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 itzune/morpheus-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf itzune/morpheus-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 itzune/morpheus-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf itzune/morpheus-gguf:Q4_K_M

Use Docker

docker model run hf.co/itzune/morpheus-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use itzune/morpheus-gguf with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/itzune/morpheus-gguf:Q4_K_M

Ollama
How to use itzune/morpheus-gguf with Ollama:
```
ollama run hf.co/itzune/morpheus-gguf:Q4_K_M
```

Unsloth Studio

How to use itzune/morpheus-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 itzune/morpheus-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 itzune/morpheus-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for itzune/morpheus-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use itzune/morpheus-gguf with Docker Model Runner:
```
docker model run hf.co/itzune/morpheus-gguf:Q4_K_M
```

Lemonade

How to use itzune/morpheus-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull itzune/morpheus-gguf:Q4_K_M

Run and chat with the model

lemonade run user.morpheus-gguf-Q4_K_M

List all available models

lemonade list

Morpheus v2 (Mamba-2) — Basque Autocomplete (GGUF)

GGUF quantized versions of itzune/morpheus, a 91M-parameter Mamba-2 language model for on-device Basque (Euskara) text autocompletion.

Available Quantizations

File	Quant	Size	BPW	Use Case
`morpheus-v2-mamba.Q4_K_M.gguf`	Q4_K_M	55 MB	4.64	Recommended for deployment (best size/quality tradeoff)
`morpheus-v2-mamba.Q5_K_M.gguf`	Q5_K_M	66 MB	5.60	Higher quality, preserves Basque morphology better

Model Details

Architecture: Mamba-2 (State Space Model)
Parameters: 91M
Checkpoint: step 74,000 (best, held-out PPL 7.13)
Training tokens: ~10 billion
Tokenizer: 4K Unigram SentencePiece (included in base model repo)
Trained without BOS token

Usage with llama.cpp

# Start the server
llama-server -m morpheus-v2-mamba.Q5_K_M.gguf --host 0.0.0.0 --port 8080 -ngl 0

# Or use the CLI
llama-cli -m morpheus-v2-mamba.Q5_K_M.gguf -p "Kaixo, zer moduz" -n 50

Important: llama.cpp version

Requires llama.cpp built from source after 2025-07-04 (commit dc2187d48 or later), which fixes the SSM_SCAN computation for Mamba-2 models with n_groups > 1. Earlier builds produce silently incorrect greedy outputs.

Tokenizer Notes

The SentencePiece tokenizer diverges from llama.cpp's built-in SP tokenizer for this vocabulary. For faithful inference, use token-ID prompts or ensure the demo server's tokenization matches training semantics (no BOS token).

Inference Engineering

The deployed demo uses several strategies to handle subword tokenization in an interactive keyboard context:

Retokenization fallback (query shorter prefixes when the typed prefix tokenizes poorly)
Sticky merge (carry forward candidates from previous keystrokes)
Top-k exceeding display-k (fetch 5, display 3)
Next-word candidate extraction

See the accompanying paper for details.

Citation

@misc{morpheus_v2_mamba,
  author = {Xabier Ezpeleta},
  title = {Morpheus v2: On-Device Basque Autocompletion with Mamba-2},
  year = {2026},
}

Downloads last month: -

GGUF

Model size

94.1M params

Architecture

mamba2

Hardware compatibility

4-bit

5-bit

Model tree for itzune/morpheus-gguf

Base model

itzune/morpheus

Quantized

(1)

this model