Model reference · open weights
Laguna-S-2.1 is an open-weight language model from poolside, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Laguna S 2.1 Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, designed for agentic coding and long-horizon work. It sits between Laguna XS 2.1 (33B-A3B) and Laguna M.1 (225B-A23B) in the Laguna series and shares the family recipe: a token-choice router with softplus gating over 256 routed experts plus one shared expert, grouped-query attention, and interleaved full/sliding-window attention. [!NOTE] Laguna S 2.1 is released under OpenMDW-1.1, a fully permissive license. Use it, modify it, and build commercial products on it. No permission required. If you want more than the weights: production support, latency and cost optimization, or output indemnification, talk to us. Highlights - Mixed SWA and global attention layout: 48 layers in a 1:3 global-to-SWA ratio (12 global attention layers, 36 sliding-window layers, window 512), with softplus attention gating and per-layer-type rotary scales - 1M context: 1,048,576-token context window - Native reasoning support: interleaved thinking between tool calls, with per-request control via enablethinking - Speculative decoding: a trained DFlash draft model is available for lower-latency serving - Quantized variants: FP8, NVFP4, INT4 and GGUF - OpenMDW-1.1 license: Use and modify the model and associated materials freely for commercial and non-commercial purposes (learn more about OpenMDW) Model overview - Number of parameters: 118B total, ~8B activated per token - Layers: 48 (12 global attention, 36 sliding-window attention) - Experts: 256 routed (top-10) plus 1 shared expert - Attention: grouped-query, 8 KV heads, head dim 128; per-head softplus output gating - Sliding window: 512 tokens - Context window: 1,048,576 tokens - Vocabulary: 100,352 tokens (Laguna family tokenizer) - Modality: text-to-text - Reasoning: interleaved thinking with preserved thinking Benchmark results Benchmarks as of 21 July 2026. Laguna S 2.1 in bold; a dash (-) marks a benchmark a model was not evaluated on. Scores marked are as reported by third parties: Terminal-Bench 2.1 and DeepSWE via Artificial Analysis, SWE Atlas via Scale AI's official leaderboard, and Toolathlon Verified via its off
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | poolside |
|---|---|
| Type | Language models |
| Parameters (lead) | 117.6B |
| Context | 1024k tokens |
| Variants | 1 |
| Runs with | transformers |
| Released | 2026-07-13 |
| Popularity | 55k downloads / month |
| Likes | 1,008 |
| Licence | Open, with conditions |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Laguna-S-2.1 | 117.6B | BF16 | ~270.4 GB | — | Weights ↗ |
Using it via the API
Once AxForge deploys laguna-s-2-1 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (laguna-s-2-1 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"laguna-s-2-1","messages":[{"role":"user","content":"Hello"}]}'
Details
Tags
Licence
Open weights under openmdw-1.1, which carries conditions (e.g. attribution or an acceptable-use clause). Worth a read before production use — we can walk you through it. Read the licence ↗