selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

mehdi-hf logo

cilla-mini

mehdi-hf·released 16 Nov 2026

CC BY-NC 4.028M≈0.6 GBgated
Runs on CPU or any GPU≈53 MB of weights
hf download mehdi-hf/cilla-mini
Setup ↓

Gated, non-commercial (CC BY-NC 4.0): ask for access on this page. Cilla Mini is the 18M model for CPUs, phones and browsers: Cilla shrunk with Kyutai's small-model recipe (8 layers, a 64-dim interface, a one-step drifting sampler head, the 2.6M Mimi decoder), guidance baked in.

How much VRAM does cilla-mini need?

At FP16 / BF16 cilla-mini needs about 0.6 GB of GPU memory.

--vram
any
--gpus
--quant
QuantisationWeightsTotal
4-bitRecommended default for local use0.0 GB ≈0.5 GB
8-bitLossless in practice, twice the size of Q40.0 GB ≈0.5 GB
FP16 / BF16recommendedFull precision, as released0.1 GB ≈0.6 GB

Estimates for the weights plus runtime overhead; activations vary with resolution and batch size. Pick a GPU above and the fit column checks every row against it.

Can the RTX 4060 run cilla-mini? →

Run cilla-mini locally

No runtime support recorded yet. Most models also run through Hugging Face Transformers.

About cilla-mini

Gated, non-commercial (CC BY-NC 4.0): ask for access on this page. Cilla Mini is the 18M model for CPUs, phones and browsers: Cilla shrunk with Kyutai's small-model recipe (8 layers, a 64-dim interface, a one-step drifting sampler head, the 2.6M Mimi decoder), guidance baked in. It speaks Persian in the voice of a short audio prompt. Built on Pocket TTS by Kyutai. Try it in your browser · Run it on a Mac · Phonon runtime · Browser library · Python package Audio made per second of work ("real time" is 1x): speak_fa.py normalises the text, speaks one sentence at a time from the same prompt, trims the silence each piece opens with and joins them with a short pause. Do the same in your own code: cutting a sentence into 50-token pieces (the old Pocket TTS default) made these models repeat words, once the name «ساندر پیچای» twice in a row. The released package is enough (pocket-tts 4.0.1 or newer, checked for this repo). config.yaml sets capitalize_first_letter, append_terminal_punctuation and pad_with_spaces_for_short_inputs to false: leave them, otherwise the package upper-cases or drops the first letters of Persian text. The phonon/ folder has the model for the Phonon runtime (Rust, no PyTorch, no GPU) and the same Persian front-end. Apple silicon: Details, options and notes: phonon/README.md.

Full model card on Hugging Face →

Other Cilla models

Whole family →
mehdi-hf logo
cilla-litemehdi-hf
110MNon-commercial≈0.7 GB↓ 0

Alternatives to cilla-mini

All alternatives →
MBZUAI logo

LLMVoX

MBZUAI·TTS

≈0.6 GB

This repository contains the model as described in LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM.

30MCC BY-NC-SA 4.0
1.9KMar 2025
hexgrad logo

Kokoro-82M

hexgrad·TTS

≈0.7 GB

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient.

82MApache 2.0
13.1MDec 2024gguf
zaakirio logo

kokoro-ru

zaakirio·TTS

≈0.7 GB

Russian text-to-speech at 82M parameters, running 9.8x faster than realtime on a laptop CPU with no GPU. Three fixed voices from consented studio actors.

82MOpenRAIL
72.7KJul 2026
facebook logo

mms-tts-eng

facebook·TTS

≈0.6 GB

This repository contains the English (eng) language text-to-speech (TTS) model checkpoint.

36MCC BY-NC 4.0
53.3KAug 2023
facebook logo

mms-tts-hin

facebook·TTS

≈0.6 GB

This repository contains the Hindi (hin) language text-to-speech (TTS) model checkpoint.

36MCC BY-NC 4.0
8.9KSept 2023
OpenMOSS-Team logo

MOSS-TTS-Nano-100M

OpenMOSS-Team·TTS

≈0.7 GB

MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run directly on CPU without a GPU, and keeps the deployment stack simple enough for local demos, web serving…

100M32K ctx Apache 2.0
122.3KApr 2026gguf

cilla-mini FAQ

How much VRAM does cilla-mini need?
About 0.6 GB at FP16 / BF16.
Can cilla-mini run on the RTX 4060?
Yes. It fits at FP16 / BF16 (about 0.6 GB). It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
Can I use cilla-mini commercially?
No. It is released under CC BY-NC 4.0. Non-commercial use only, with attribution.

Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.