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.

cilla-mini

Side-by-side specs, memory needs, licence, runtimes and benchmarks. Add up to 4 models.

--vram
any
--gpus
--quant
--add

On your GPU

  • cilla-mini
Property
Overview
TaskTTS
Parameters28M
Active parametersdense
Context length—
Input → output
Released16 Nov 2026
LicenceCC BY-NC 4.0
Gated downloadyes, accept terms
Memory and speed
Fits your hardwarepick a GPU above≈0.6 GB
VRAM at Q4≈0.5 GB
VRAM at Q8≈0.5 GB
VRAM at FP16≈0.6 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days0
Likes58
Runs with
Ollama tag—
Architecture
Weights dtypefloat32
GGUF availableno

Keep comparing

Memory figures are estimates for an 8K context at the chosen quantisation (Q4_K_M for LLMs by default). Speeds are rough, memory-bound estimates. Self-reported benchmark scores come from the model authors.