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.

Inkling-2-Small

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

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

On your GPU

  • Inkling-2-Small
Property
Overview
TaskVision
Parameters383B
Active parametersdense
Context length1M
Input → output
Released4 Nov 2026
LicenceApache 2.0
Gated downloadno
Memory and speed
Fits your hardwarepick a GPU above≈229 GB
VRAM at Q4≈229 GB
VRAM at Q8≈400 GB
VRAM at FP16≈751 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days45.4K
Likes634
Runs with
Ollama
Transformers
Ollama taginkling-2-small
Architecture
ArchitectureInkling2ForConditionalGeneration
Layers48
Attention / KV heads48 / 8
Vocabulary201 024
Weights dtypebfloat16
GGUF availableyes

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.