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.

Bielik-11B-v3.1-Instruct

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

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

On your GPU

  • Bielik-11B-v3.1-Instruct
Property
Overview
TaskChat
Parameters11.2B
Active parametersdense
Context length32K
Input → output
Released26 Oct 2026
LicenceApache 2.0
Gated downloadyes, accept terms
Memory and speed
Fits your hardwarepick a GPU above≈8.3 GB
VRAM at Q4≈8.3 GB
VRAM at Q8≈13 GB
VRAM at FP16≈24 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days377
Likes24
Runs with
Jan
KoboldCpp
llama.cpp
LM Studio
LocalAI
MLX
Ollama
SGLang
Text Generation Inference
Transformers
vLLM
Ollama tag—
Architecture
ArchitectureLlamaForCausalLM
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.