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

Laguna S 2.1 MLX 4bit by Vontra

 »  All LLMs  »  Vontra  »  Laguna S 2.1 MLX 4bit   URL Share it on

  493   

Laguna S 2.1 MLX 4bit is an open-source language model by Vontra. Features: 117.6b LLM, VRAM: 65.8GB, Context: 1024K, License: openmdw-1.1, Quantized, LLM Explorer Score: 0.34.

  4-bit   4bit   Agentic-coding   Apple-silicon Base model:poolside/laguna-s-2... Base model:quantized:poolside/...   Code   Conversational   Custom code   En   Laguna   Mixture-of-experts   Mlx   Mlx-lm   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Vontra/Laguna-S-2.1-MLX-4bit 

Laguna S 2.1 MLX 4bit Benchmarks

LLME Score: 0.34462
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Laguna S 2.1 MLX 4bit (Vontra/Laguna-S-2.1-MLX-4bit)

Laguna S 2.1 MLX 4bit Parameters and Internals

LLM NameLaguna S 2.1 MLX 4bit
Repository 🤗https://huggingface.co/Vontra/Laguna-S-2.1-MLX-4bit 
Base Model(s)  poolside/Laguna-S-2.1   poolside/Laguna-S-2.1
Model Size117.6b
Required VRAM65.8 GB
Updated2026-07-23
MaintainerVontra
Model Typelaguna
Model Files  5.3 GB: 1-of-13   5.2 GB: 2-of-13   5.1 GB: 3-of-13   5.1 GB: 4-of-13   5.1 GB: 5-of-13   5.1 GB: 6-of-13   5.1 GB: 7-of-13   5.1 GB: 8-of-13   5.1 GB: 9-of-13   5.1 GB: 10-of-13   5.1 GB: 11-of-13   5.1 GB: 12-of-13   4.3 GB: 13-of-13
Supported Languagesen
Quantization Type4bit
Model ArchitectureLagunaForCausalLM
Licenseopenmdw-1.1
Context Length1048576
Model Max Length1048576
Tokenizer ClassTokenizersBackend
Padding Token〈|PAD|〉
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Laguna S 2.1 MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Laguna S 2.1 MLX 6bit1024K / 95.4 GB4572
Laguna S 2.11024K / 214.2 GB13285496
Laguna S 2.11024K / 214.2 GB404
Note: green Score (e.g. "73.2") means that the model is better than Vontra/Laguna-S-2.1-MLX-4bit.

Rank the Laguna S 2.1 MLX 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? 55346 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer