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

Fikri 3.1 8B Instruct by BrewInteractive

 »  All LLMs  »  BrewInteractive  »  Fikri 3.1 8B Instruct   URL Share it on

  75   

Fikri 3.1 8B Instruct is an open-source language model by BrewInteractive. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: llama3.1, Quantized, Instruction-Based, Merged, LLM Explorer Score: 0.16.

  Merged Model   Arxiv:2405.09673   4bit Base model:finetune:unsloth/me... Base model:unsloth/meta-llama-...   Conversational Dataset:brewinteractive/alpaca...   Instruct   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Tr
Model Card on HF 🤗: https://huggingface.co/BrewInteractive/fikri-3.1-8B-Instruct 

Fikri 3.1 8B Instruct Benchmarks

LLME Score: 0.16341
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Fikri 3.1 8B Instruct (BrewInteractive/fikri-3.1-8B-Instruct)
🌟 Advertise your project 🚀

Fikri 3.1 8B Instruct Parameters and Internals

Model Type 
Language Model
Use Cases 
Primary Use Cases:
Understanding and generation of Turkish text
Additional Notes 
Fikri is the first and lightest in the lineup, fine-tuned specifically for low-stream Turkish tasks. It is suitable for applications like conversational AI and text summarization due to its efficiency and relevance to Turkish language nuances.
Supported Languages 
Turkish (fluent)
Training Details 
Data Volume:
~1B tokens of high-quality Turkish data
Hardware Used:
2x NVIDIA RTX 4090 GPU
Model Architecture:
LoRA configuration with r = 128, lora_alpha = 32, learning_rate = 5e-5
LLM NameFikri 3.1 8B Instruct
Repository 🤗https://huggingface.co/BrewInteractive/fikri-3.1-8B-Instruct 
Base Model(s)  unsloth/Meta-Llama-3.1-8B-bnb-4bit   unsloth/Meta-Llama-3.1-8B-bnb-4bit
Merged ModelYes
Model Size8b
Required VRAM16.1 GB
Updated2026-04-11
MaintainerBrewInteractive
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagestr
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licensellama3.1
Context Length8192
Model Max Length8192
Transformers Version4.43.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Fikri 3.1 8B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB162
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB91
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB32
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB60
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB52925
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB30717
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB63
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB01
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB161
...B Instruct 262k V2 EXL2 6.0bpw256K / 6.7 GB41

Rank the Fikri 3.1 8B 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? 52721 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