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.

NLD-Uni

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

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

On your GPU

  • NLD-Uni
Property
Overview
TaskOmni
Parameters18.3B
Active parametersdense
Context length128K
Input → output
Released5 Oct 2026
LicenceUnknown licence
Gated downloadno
Memory and speed
Fits your hardwarepick a GPU above≈12 GB
VRAM at Q4≈12 GB
VRAM at Q8≈21 GB
VRAM at FP16≈37 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days1.3K
Likes12
Runs with
Transformers
Ollama tag—
Architecture
ArchitectureNLDUniForCausalLM
Layers34
Attention / KV heads32 / 8
Vocabulary132 101
Weights dtypebfloat16
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.