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.

Crowd-v1

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

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

On your GPU

  • Crowd-v1
Property
Overview
TaskChat
Parameters1B
Active parametersdense
Context length—
Input → output
Released21 Aug 2026
LicenceMIT
Gated downloadno
Memory and speed
Fits your hardwarepick a GPU above≈1.4 GB
VRAM at Q4≈1.4 GB
VRAM at Q8≈1.9 GB
VRAM at FP16≈2.8 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days91K
Likes39
Runs with
Ollama tag—
Architecture
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.