Laguna XS 2.1 8bit is an open-source language model by mlx-community. Features: 9.4b LLM, VRAM: 35.6GB, Context: 256K, License: openmdw-1.1, Quantized, LLM Explorer Score: 0.29.
8-bit 8bit Base model:poolside/laguna-xs-... Base model:quantized:poolside/... Conversational Custom code Eval-results Laguna Mlx Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Laguna-XS-2.1-8bit
Laguna XS 2.1 8bit 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 XS 2.1 8bit Parameters and Internals
| LLM Name | Laguna XS 2.1 8bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Laguna-XS-2.1-8bit |
| Base Model(s) | |
| Model Size | 9.4b |
| Required VRAM | 35.6 GB |
| Updated | 2026-07-22 |
| Maintainer | mlx-community |
| Model Type | laguna |
| Model Files | |
| Quantization Type | 8bit |
| Model Architecture | LagunaForCausalLM |
| License | openmdw-1.1 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | 〈|PAD|〉 |
| Vocabulary Size | 100352 |
Rank the Laguna XS 2.1 8bit 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? 55294 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a