Laguna XS 2.1 DFlash is an open-source language model by poolside. Features: 462.1m LLM, VRAM: 0.9GB, Context: 256K, License: openmdw-1.1, LLM Explorer Score: 0.33.
Arxiv:2602.06036 Base model:finetune:poolside/l... Base model:poolside/laguna-xs-... Dflash Laguna Region:us Safetensors Speculative-decoding Speculators
Model Card on HF 🤗: https://huggingface.co/poolside/Laguna-XS-2.1-DFlash
Laguna XS 2.1 DFlash 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 DFlash Parameters and Internals
| LLM Name | Laguna XS 2.1 DFlash |
| Repository 🤗 | https://huggingface.co/poolside/Laguna-XS-2.1-DFlash |
| Base Model(s) | |
| Model Size | 462.1m |
| Required VRAM | 0.9 GB |
| Updated | 2026-07-27 |
| Maintainer | poolside |
| Model Type | laguna |
| Model Files | |
| Model Architecture | DFlashLagunaForCausalLM |
| License | openmdw-1.1 |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Vocabulary Size | 100352 |
| Torch Data Type | bfloat16 |
Rank the Laguna XS 2.1 DFlash 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? 55446 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