Instructions to use mashbox-labs/maya1-TPU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use mashbox-labs/maya1-TPU 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 mashbox-labs/maya1-TPU:BF16 # Run inference directly in the terminal: llama cli -hf mashbox-labs/maya1-TPU:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf mashbox-labs/maya1-TPU:BF16 # Run inference directly in the terminal: llama cli -hf mashbox-labs/maya1-TPU:BF16
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf mashbox-labs/maya1-TPU:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf mashbox-labs/maya1-TPU:BF16
Use Docker
docker model run hf.co/mashbox-labs/maya1-TPU:BF16
- Llama new
- LM Studio
- Jan
- Ollama
How to use mashbox-labs/maya1-TPU with Ollama:
ollama run hf.co/mashbox-labs/maya1-TPU:BF16
- Unsloth Desktop
- Docker Model Runner
How to use mashbox-labs/maya1-TPU with Docker Model Runner:
docker model run hf.co/mashbox-labs/maya1-TPU:BF16
- Lemonade
How to use mashbox-labs/maya1-TPU with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull mashbox-labs/maya1-TPU:BF16
Run and chat with the model
lemonade run user.maya1-TPU-BF16
List all available models
lemonade list
- Atomic Chat

maya1 and the SNAC 24 kHz decoder
Weights only: the mashbox package, release 0.1.10, has no mashbox run command for this model. To make speech, run the original weights with Maya Research's Transformers example, which needs a CUDA GPU.
Maya Research's maya1 text-to-speech model as one BF16 GGUF file, with the SNAC 24 kHz decoder it speaks through as NumPy arrays. maya1 reads a voice description and the text to say, then writes SNAC audio codes; the SNAC decoder makes 24 kHz audio from those codes. Upstream lists 17 emotion tags, such as <laugh> and <whisper>, that go inline in the text.
Files
| File | What | Size | Tensors | From upstream |
|---|---|---|---|---|
maya1-BF16.gguf |
maya1, llama architecture, 28 blocks | 6.60 GB | 255, BF16 (norms and rope factors F32) | maya-research/maya1 safetensors |
snac/snac_24khz_decoder.npz |
SNAC quantizer codebooks and decoder | 52.5 MB | 104 arrays, float32 | hubertsiuzdak/snac_24khz pytorch_model.bin |
snac/LICENSE |
SNAC's licence file | hubertsiuzdak/snac |
The GGUF holds the weights and model settings. It has no tokenizer, so llama.cpp cannot load it on its own: the tokenizer, chat template, voice description format (prompt.txt) and emotion list (emotions.txt) are in maya-research/maya1.
Load
Both files open with standard Python readers:
pip install gguf huggingface_hub numpy
import numpy as np
from gguf import GGUFReader
from huggingface_hub import hf_hub_download
lm = GGUFReader(hf_hub_download("mashbox-labs/maya1-TPU", "maya1-BF16.gguf"))
print(len(lm.tensors), lm.tensors[0].name) # 255 token_embd.weight
snac = np.load(hf_hub_download("mashbox-labs/maya1-TPU", "snac/snac_24khz_decoder.npz"))
print(snac["decoder.model.7.weight"].shape) # (1, 64, 7)
Links
| Original model | maya-research/maya1 by Maya Research |
| Audio codec | hubertsiuzdak/snac_24khz by Hubert Siuzdak |
| Companies | hello@mashbox.gg |
Licence
maya1: Apache-2.0, as stated by maya-research/maya1 in its model card. That repo has no separate licence file.
SNAC decoder: MIT, as stated by hubertsiuzdak/snac_24khz. snac/LICENSE is the licence file of the SNAC code repo, hubertsiuzdak/snac, unchanged.
- Downloads last month
- 48
16-bit