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

Meta Llama 3 8B Instruct 64K 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  Meta Llama 3 8B Instruct 64K 4bit   URL Share it on

  22   

Meta Llama 3 8B Instruct 64K 4bit is an open-source language model by mlx-community. Features: 8b LLM, VRAM: 75GB, Context: 64K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

  4bit   Conversational   En   Facebook   Instruct   Llama   Llama-3   Meta   Mlx   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Meta-Llama-3-8B-Instruct-64k-4bit 

Meta Llama 3 8B Instruct 64K 4bit Benchmarks

LLME Score: 0.13021
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Meta Llama 3 8B Instruct 64K 4bit (mlx-community/Meta-Llama-3-8B-Instruct-64k-4bit)
🌟 Advertise your project 🚀

Meta Llama 3 8B Instruct 64K 4bit Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model was converted to MLX format from `NurtureAI/Meta-Llama-3-8B-Instruct-64k` using mlx-lm version 0.11.0.
LLM NameMeta Llama 3 8B Instruct 64K 4bit
Repository 🤗https://huggingface.co/mlx-community/Meta-Llama-3-8B-Instruct-64k-4bit 
Base Model(s)  ...a Llama 3 8B Instruct 64K PoSE   Azma-AI/Meta-Llama-3-8B-Instruct-64k-PoSE
Model Size8b
Required VRAM75 GB
Updated2026-04-23
Maintainermlx-community
Model Typellama
Instruction-BasedYes
Model Files  5.2 GB: 1-of-15   5.2 GB: 2-of-15   5.4 GB: 3-of-15   5.1 GB: 4-of-15   5.2 GB: 5-of-15   5.2 GB: 6-of-15   5.4 GB: 7-of-15   5.1 GB: 8-of-15   5.2 GB: 9-of-15   5.2 GB: 10-of-15   5.4 GB: 11-of-15   5.1 GB: 12-of-15   5.2 GB: 13-of-15   5.2 GB: 14-of-15   1.9 GB: 15-of-15   4.5 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length65536
Model Max Length65536
Transformers Version4.40.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Meta Llama 3 8B Instruct 64K 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB162
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB101
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB92
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB50
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB62325
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB30717
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB53
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB51
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB271
...B Instruct 262k V2 EXL2 8.0bpw256K / 8.4 GB70
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Meta-Llama-3-8B-Instruct-64k-4bit.

Rank the Meta Llama 3 8B Instruct 64K 4bit 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? 53185 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