What are the hardware requirements for Bielik 11B V2.2 Instruct?

Bielik 11B V2.2 Instruct requires approximately 22.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Bielik 11B V2.2 Instruct and how large is it?

Bielik 11B V2.2 Instruct is developed by speakleash, a model with 11b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Bielik 11B V2.2 Instruct?

Bielik 11B V2.2 Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Bielik 11B V2.2 Instruct by speakleash — VRAM 22.3GB

Name: Bielik 11B V2.2 Instruct
Author: speakleash

Bielik 11B V2.2 Instruct is an open-source language model by speakleash. Features: 11b LLM, VRAM: 22.3GB, License: proprietary, Fine-Tuned, Instruction-Based, LLM Explorer Score: 0.24.

Arxiv:2005.01643 Arxiv:2006.09092 Arxiv:2309.11235 Arxiv:2402.13228 Arxiv:2410.18565 Base model:finetune:speakleash... Base model:speakleash/bielik-1... Conversational Endpoints compatible Finetuned Instruct Mistral Pl Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct

Bielik 11B V2.2 Instruct Benchmarks

LLME Score: 0.23998

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Bielik 11B V2.2 Instruct (speakleash/Bielik-11B-v2.2-Instruct)

🌟 Advertise your project 🚀

Bielik 11B V2.2 Instruct Parameters and Internals

LLM Name	Bielik 11B V2.2 Instruct
Repository 🤗	https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct
Base Model(s)	Bielik 11B V2 speakleash/Bielik-11B-v2
Model Size	11b
Required VRAM	22.3 GB
Updated	2026-05-03
Maintainer	speakleash
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-5 5.0 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 2.6 GB: 5-of-5
Supported Languages	pl
Gated Model	Yes
Model Architecture	AutoModelForCausalLM
License	proprietary

Quantized Models of the Bielik 11B V2.2 Instruct

Model	Likes	Downloads	VRAM
... 11B V2.2 Instruct EXL2 4.5bit	3	462	6 GB
Bielik 11B V2.2 Instruct GPTQ	3	379	6 GB
... 11B V2.2 Instruct Quanto 8bit	4	209	12 GB
Bielik 11B V2.2 Instruct AWQ	3	176	6 GB
Bielik 11B V2.2 Instruct FP8	3	119	11 GB
...B V2.2 Instruct HQQ 4bit 128gs	3	98	6 GB
...B V2.2 Instruct HQQ 8bit 128gs	3	65	11 GB
Bielik 11B V2.2 Instruct W8A8	3	19	11 GB

Best Alternatives to Bielik 11B V2.2 Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Bielik 11B V3.0 Instruct	0K / 22.3 GB	280093	60
...elik Minitron 7B V3.0 Instruct	0K / 15 GB	28742	24
Bielik PL 11B V3.0 Instruct	0K / 22.4 GB	2492	8
Bielik 11B V2.3 Instruct	0K / 22.3 GB	12401	52
Bielik 11B V2.1 Instruct	0K / 22.3 GB	1602	3
Bielik 11B V2.6 Instruct	0K / 22.4 GB	1983	43
Bielik 11B V2.0 Instruct	0K / 22.3 GB	34	5
Bielik 11B V2.5 Instruct	0K / 22.3 GB	0	9

Note: green Score (e.g. "73.2") means that the model is better than speakleash/Bielik-11B-v2.2-Instruct.

Rank the Bielik 11B V2.2 Instruct Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Bielik 11B V2.2 Instruct by speakleash