LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Bielik 11B V2.2 Instruct HQQ 4bit 128gs by speakleash

 »  All LLMs  »  speakleash  »  Bielik 11B V2.2 Instruct HQQ 4bit 128gs   URL Share it on

  98   

Bielik 11B V2.2 Instruct HQQ 4bit 128gs is an open-source language model by speakleash. Features: 11b LLM, VRAM: 6.2GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.15.

  4bit Base model:finetune:speakleash... Base model:speakleash/bielik-1...   Conversational   Finetuned   Gguf   Instruct   Mistral   Pl   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-HQQ-4bit-128gs 

Bielik 11B V2.2 Instruct HQQ 4bit 128gs Benchmarks

LLME Score: 0.14935
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bielik 11B V2.2 Instruct HQQ 4bit 128gs (speakleash/Bielik-11B-v2.2-Instruct-HQQ-4bit-128gs)
🌟 Advertise your project 🚀

Bielik 11B V2.2 Instruct HQQ 4bit 128gs Parameters and Internals

Model Type 
causal decoder-only
Additional Notes 
HQQ format model files; note on potential quality reduction due to quantization.
Supported Languages 
Polish (fluent)
Input Output 
Performance Tips:
Quantised models may show reduced response quality and possible hallucinations.
LLM NameBielik 11B V2.2 Instruct HQQ 4bit 128gs
Repository 🤗https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-HQQ-4bit-128gs 
Base Model(s)  speakleash/Bielik-11B-v2.2-Instruct   speakleash/Bielik-11B-v2.2-Instruct
Model Size11b
Required VRAM6.2 GB
Updated2026-05-25
Maintainerspeakleash
Model Typemistral
Instruction-BasedYes
Model Files  6.2 GB
Supported Languagespl
GGUF QuantizationYes
Quantization Typegguf|4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32128
Torch Data Typebfloat16

Best Alternatives to Bielik 11B V2.2 Instruct HQQ 4bit 128gs

Best Alternatives
Context / RAM
Downloads
Likes
... 11B V2.2 Instruct EXL2 4.5bit32K / 6.5 GB4623
...B V2.2 Instruct HQQ 8bit 128gs32K / 11.7 GB653
Bielik 11B V2.2 Instruct GPTQ32K / 6.2 GB3793
Bielik 11B V2.2 Instruct AWQ32K / 6.2 GB1763
... 11B V2.2 Instruct Quanto 8bit32K / 12 GB2094
Bielik 11B V2.2 Instruct FP832K / 11.4 GB1193
Bielik 11B V2.2 Instruct W8A832K / 11.5 GB193
...elik V2.3 Instruct MedIT Merge32K / 22.3 GB12802
...elik V2.3 Instruct Llama Prune32K / 15.4 GB13150
Mistral 11B Instruct V0.132K / 42.9 GB730
Note: green Score (e.g. "73.2") means that the model is better than speakleash/Bielik-11B-v2.2-Instruct-HQQ-4bit-128gs.

Rank the Bielik 11B V2.2 Instruct HQQ 4bit 128gs 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? 53972 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