Laguna-S-2.1-GGUF

You can now run Laguna-S-2.1 in Unsloth Studio or llama.cpp To run or train any LLM with a open-source UI, install Unsloth Studio via: macOS, Linux, WSL: Windows: Running Unsloth's `UD-Q4_K_XL` with llama.cpp The GGUFs in this repo are Unsloth Dynamic 2.0 quants (imatrix calibrated). Laguna support is available starting from llama.cpp release b10087. Use this release or a newer one. Download the `UD-Q4_K_XL` shards (~40GB, split into 3 files): Serve it with `llama-server` (pass the first shard; the remaining shards load automatically): Or run a one-off generation with `llama-cli`: [!NOTE] `-ngl 99` offloads all layers to GPU; lower it (or drop it) if you run out of VRAM. Use on OpenRouter · Use on Vercel AI Gateway · Release blog post 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. 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 `enable_thinking` **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-win