LLM EXPLORER 59,420 MODELS INDEXED

Bielik 11B V2.5 Instruct FP8 Dynamic by speakleash

By speakleash · 33 downloads
HF Repo ↗ Copy URL

Bielik 11B V2.5 Instruct FP8 Dynamic is an open-source language model by speakleash. Features: 11b LLM, VRAM: 11.5GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.18.

  8bit Base model:quantized:speakleas... Base model:speakleash/bielik-1...   Compressed-tensors   Conversational   Finetuned   Gguf   Instruct   Llama   Pl   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/speakleash/Bielik-11B-v2.5-Instruct-FP8-Dynamic 

Bielik 11B V2.5 Instruct FP8 Dynamic Parameters and Internals

LLM NameBielik 11B V2.5 Instruct FP8 Dynamic
Repository 🤗https://huggingface.co/speakleash/Bielik-11B-v2.5-Instruct-FP8-Dynamic 
Base Model(s)  speakleash/Bielik-11B-v2.5-Instruct   speakleash/Bielik-11B-v2.5-Instruct
Model Size11b
Required VRAM11.5 GB
Updated2026-07-26
Maintainerspeakleash
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   1.5 GB: 3-of-3
Supported Languagespl
Quantization Type8bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.52.4
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32128
Torch Data Typefloat16

Best Alternatives to Bielik 11B V2.5 Instruct FP8 Dynamic

Best Alternatives
Context / RAM
Downloads
Likes
A6.11024K / 16.1 GB1300
...k PL 11B V3.0 Instruct Heretic32K / 22.3 GB1490
Llama 3 11B Instruct RP GLUED8K / 22.2 GB43
Llama 3 11B Instruct8K / 22.1 GB63
Llama 3 Synatra 11B V18K / 23 GB712
Llama 3 16B Instruct V0.18K / 33.5 GB175
SyntheticMoist 11B V24K / 21.4 GB73
Antares 11B V14K / 21.4 GB162
MedMitsu Instruct 11B4K / 21.4 GB90
Tengentoppa 11B Instruct2K / 23.2 GB90
Note: green Score (e.g. "73.2") means that the model is better than speakleash/Bielik-11B-v2.5-Instruct-FP8-Dynamic.