Laguna S 2.1 OQ6e is an open-source language model by mlx-community. Features: 24.1b LLM, VRAM: 91.9GB, Context: 1024K, License: openmdw-1.1, LLM Explorer Score: 0.36.
6-bit Base model:poolside/laguna-s-2... Base model:quantized:poolside/... Conversational Custom code Laguna Mlx Moe Oq Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Laguna-S-2.1-oQ6e
Laguna S 2.1 OQ6e Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Laguna S 2.1 OQ6e Parameters and Internals
| LLM Name | Laguna S 2.1 OQ6e |
| Repository 🤗 | https://huggingface.co/mlx-community/Laguna-S-2.1-oQ6e |
| Base Model(s) | |
| Model Size | 24.1b |
| Required VRAM | 91.9 GB |
| Updated | 2026-07-23 |
| Maintainer | mlx-community |
| Model Type | laguna |
| Model Files | |
| Model Architecture | LagunaForCausalLM |
| License | openmdw-1.1 |
| Context Length | 1048576 |
| Model Max Length | 1048576 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | 〈|PAD|〉 |
| Vocabulary Size | 100352 |
| Torch Data Type | bfloat16 |
Rank the Laguna S 2.1 OQ6e 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! 🌟
What open-source LLMs or SLMs are you in search of? 55346 in total.
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a