Liquid
Laguna S 2.1
Laguna S 2.1 is an open-weights model by Liquid. It holds an Intelligence score of 71.6 on the local.ai leaderboard (2026-08 snapshot).
open weights
71.6
local.ai Intelligence
Parameters
undisclosed
Benchmarks (local.ai snapshot)
HuggingFace metadata · updated 2026-07-27
Metadata refreshed from the HuggingFace API (snapshot 2026-08-15T15:53:42.405Z). Context length and long-form descriptions are the next pipeline stage.
Does it fit your hardware?
Detect or select your GPU first. Green = weights + context headroom, yellow = tight, grey = does not fit.
Params not disclosed — no size estimate.Actual files on HuggingFace
| File | Size |
|---|---|
| model-00002-of-00046.safetensors | 4.77 GB |
| model-00019-of-00046.safetensors | 4.76 GB |
| model-00020-of-00046.safetensors | 4.76 GB |
| model-00021-of-00046.safetensors | 4.76 GB |
| model-00022-of-00046.safetensors | 4.76 GB |
| model-00023-of-00046.safetensors | 4.76 GB |
GGUF: poolside/Laguna-S-2.1-GGUF · 312,002 downloads
GGUF: unsloth/Laguna-S-2.1-GGUF · 208,517 downloads
| File | Size | |
|---|---|---|
| BF16/Laguna-S-2.1-BF16-00001-of-00005.gguf | 46.55 GB | download |
| BF16/Laguna-S-2.1-BF16-00002-of-00005.gguf | 46.50 GB | download |
| BF16/Laguna-S-2.1-BF16-00003-of-00005.gguf | 46.50 GB | download |
| BF16/Laguna-S-2.1-BF16-00004-of-00005.gguf | 46.50 GB | download |
| BF16/Laguna-S-2.1-BF16-00005-of-00005.gguf | 33.00 GB | download |
| Laguna-S-2.1-UD-IQ1_M.gguf | 33.19 GB | download |
| Laguna-S-2.1-UD-IQ1_S.gguf | 31.45 GB | download |
| Laguna-S-2.1-UD-IQ2_M.gguf | 34.71 GB | download |
| Laguna-S-2.1-UD-IQ2_XXS.gguf | 34.64 GB | download |
| Laguna-S-2.1-UD-IQ3_S.gguf | 45.10 GB | download |
| Laguna-S-2.1-UD-IQ3_XXS.gguf | 41.24 GB | download |
| Laguna-S-2.1-UD-Q2_K_XL.gguf | 36.96 GB | download |
What you save self-hosting this model
Uses the model's own API price when it exists; otherwise the closest commercial equivalent.
Waiting for hardware detection…
RunLocal presents third-party leaderboard data (local.ai / Exo Labs, 2026-08) with its own fit and cost estimates. Verify pricing, licenses and file sizes at the source before deploying a model.