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-Mini

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-Mini
Property
Overview
TaskVision
Parameters26.4B
Active parameters3.5B
Context length1M
Input → output
Released17 Nov 2026
LicenceApache 2.0
Gated downloadno
Memory and speed
Fits your hardwarepick a GPU above≈17 GB
VRAM at Q4≈17 GB
VRAM at Q8≈29 GB
VRAM at FP16≈53 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days7.9K
Likes3.1K
Runs with
Jan
KoboldCpp
llama.cpp
LM Studio
LocalAI
MLX
Ollama
Transformers
Ollama taginkling-2-mini
Architecture
ArchitectureInkling2LoopForConditionalGeneration
Layers24
Attention / KV heads24 / 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.