Laguna M.1 is a 225B total parameter Mixture-of-Experts model with 23B activated parameters per token designed for agentic coding and long-horizon work. > [!NOTE] > For more details on how we trained this model, including our Model Factory approach, post-training recipe, async off-policy agent RL, and evaluations, check out our release blog post and technical report. * **Large sparse MoE for agentic coding**: Laguna M.1 is a 70-layer MoE transformer with 225B total parameters and 23B activated parameters per token * **High-capacity expert routing**: After 3 dense SwiGLU layers, Laguna M.1 uses 67 sparse MoE layers with 256 experts, top-k=16 routing and auxiliary-loss-free load balancing * **Global attention architecture**: Laguna M.1 uses global attention across all layers with 64 Q-heads, 8 KV-heads and softplus attention output gating * **Native reasoning support**: Interleaved thinking between tool calls with support for enabling and disabling thinking per-request * **Strong agentic benchmark performance**: Laguna M.1 is competitive with state-of-the-art open-weight and frontier models on SWE-bench Verified, SWE-bench Multilingual, SWE-Bench Pro and Terminal-Bench 2.0 * **Apache 2.0 license**: Use and modify freely for commercial and non-commercial purposes
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Laguna M.1-NVFP4 is a 225B total parameter Mixture-of-Experts model with 23B activated parameters per token designed for agentic coding and long-horizon work. This is the NVFP4-quantized variant of Laguna M.1. > [!NOTE] > This is the NVFP4 variant. The BF16 and FP8 variants are also available on Hugging Face. *Scores shown are for the BF16 reference model; see the main Laguna M.1 model card for full benchmarking methodology. We used the highest publicly-referenced scores for all comparison models across each benchmark.*
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Laguna S 2.1 is the latest coding agent model from Poolside. Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...
Input Text→ Output Text
$0.09 / M input tokensOpenRouter · poolside/laguna-s-2.1
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DFlash speculator for the NVFP4 target poolside/Laguna-S-2.1-NVFP4. The speculator is a 6-layer Laguna-style draft model (BF16); pair it with the NVFP4 base for lower-latency serving via speculative decoding. Trained: `e0630_rhiemann_baseline` SFT, DFlash Stage-2, 15k steps. Recommended serving setting: `num_speculative_tokens=7`. DFlash upstream support is in progress (vLLM #46853, SGLang #29446, TRT-LLM #15666). Use `poolside/Laguna-S-2.1-NVFP4` as the target model.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Laguna S 2.1 is the latest coding agent model from Poolside. Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...
Input Text→ Output Text
$0 / M input tokensOpenRouter · poolside/laguna-s-2.1:free
View details ↗GGUF conversions of Laguna S 2.1 for llama.cpp, plus the DFlash speculative-decoding draft model. See the base model card for architecture details, license, and usage guidance. Serve with Poolside's llama.cpp fork, branch `laguna`, which carries full Laguna support including DFlash speculative decoding. (Base Laguna support is also in upstream review: ggml-org/llama.cpp#25165.) These GGUFs ship configured for a 262,144-token (256K) context window. This is the configuration we recommend for best output quality.
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Laguna S 2.1-NVFP4 is a 117.6B total parameter Mixture-of-Experts model with 8.5B activated parameters per token designed for agentic coding and long-horizon work on a local machine. It uses Sliding Window Attention with per-head gating in 36 out of 48 layers for fast inference and low KV cache requirements. > **Updated release (August 2026).** This is a new checkpoint that supersedes the earlier version of this repository. The weights have changed, not only the config, so if you downloaded a previous copy please re-download to pick up the current checkpoint. - **Mixed SWA and global attention layout**: Laguna S 2.1 uses softplus gating with per-layer rotary scales, enabling mixed SWA (Sliding Window Attention) and global attention layers in a 3:1 ratio (across 48 total layers) - **KV cache in FP8**: KV cache quantized to FP8, reducing memory per token - **Native reasoning support**: Interleaved thinking between tool calls with support for enabling and disabling thinking per-request - **Local-ready**: At 117.6B total parameters and 8.5B activated, the NVFP4 weights are roughly 71 GB. Available on Ollama and llama.cpp (BF16 and Q4\_K\_M only) - **OpenMDW-1.1 license**: Use and modify the model and associated materials freely for commercial and non-commercial purposes (learn more about OpenMDW)
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Laguna XS.2 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine. It uses Sliding Window Attention with per-head gating in 30 out of 40 layers for fast inference and low KV cache requirements. > [!NOTE] > For more details on how we trained this model, including on data automixing and async off-policy agent RL, check out our release blog post and technical report. - **Mixed SWA and global attention layout**: Laguna XS.2 uses sigmoid gating with per-layer rotary scales, enabling mixed SWA (Sliding Window Attention) and global attention layers in a 3:1 ratio (across 40 total layers) - **KV cache in FP8**: KV cache quantized to FP8, reducing memory per token - **Native reasoning support**: Interleaved thinking between tool calls with support for enabling and disabling thinking per-request - **Local-ready**: At 33B total parameters and 3B activated, Laguna XS.2 is compact enough to run on a Mac with 36 GB of RAM. Available on Ollama - **Apache 2.0 license**: Use and modify freely for commercial and non-commercial purposes
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside and a step forward from their Laguna XS.2 model (released in April 2026). It combines...
Input Text→ Output Text
$0.06 / M input tokensOpenRouter · poolside/laguna-xs-2.1
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside and a step forward from their Laguna XS.2 model (released in April 2026). It combines...
Input Text→ Output Text
$0 / M input tokensOpenRouter · poolside/laguna-xs-2.1:free
View details ↗Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine. This model is an upgraded version of our Laguna XS.2 model with a +5.4% jump on SWE-bench Multilingual as well as stronger performance on terminal-style tasks. > [!NOTE] > This repository contains official GGUF conversions from our standard format release built for llama.cpp (and compatible with vLLM and SGLang). To use with Ollama, pull directly with `ollama pull laguna-xs-2.1`. > > llama.cpp support is not yet upstreamed. See below. - **Mixed SWA and global attention layout**: Laguna XS 2.1 uses sigmoid gating with per-layer rotary scales, enabling mixed SWA (Sliding Window Attention) and global attention layers in a 3:1 ratio (across 40 total layers) - **KV cache in FP8**: KV cache quantized to FP8, reducing memory per token - **Native reasoning support**: Interleaved thinking between tool calls with support for enabling and disabling thinking per-request - **Local-ready**: At 33B total parameters and 3B activated, Laguna XS 2.1 is compact enough to run on a Mac with 36 GB of RAM. Available on Ollama and llama.cpp. High-quality FP8, NVFP4 and INT4 quantized variants available (see the collection) - **OpenMDW-1.1 license**: Use and modify the model and associated materials freely for commercial and non-commercial purposes (learn more about OpenMDW)
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Laguna XS 2.1-NVFP4 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine. It uses Sliding Window Attention with per-head gating in 30 out of 40 layers for fast inference and low KV cache requirements. > [!NOTE] > This is the NVFP4 variant with an FP8-quantized KV cache. The BF16, FP8 and INT4 variants are also available on Hugging Face. *We used the highest publicly-referenced scores for all comparison models across each benchmark. In all cases these were official scores published in release blog posts or equivalent, with the exception of gpt-oss-120b and Claude Haiku 4.5 where the highest published (verified) scores for SWE-Bench Pro and Terminal-Bench 2.0 are from their respective official leaderboards.*
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗