Downloads · 30 days
37
3% of all-time downloads
Laguna-S-2.1-NVFP4
AtomicChat/Laguna-S-2.1-NVFP4
Laguna-S-2.1-NVFP4 is a text generation model from AtomicChat. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as openmdw-1.1.
All-time downloads
1.2K
Public
Parameters
66.4B
67.1 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors67.1 GB · 100%
Parameter types
How the weights are stored.
U858.5B · 88%
Try a prompt
Base models
Model card
From the Hugging Face model README
<center>
<div style="display:flex; justify-content:center; align-items:center; gap:2%; max-width:560px; margin:0 auto;">
<a href="https://atomic.chat" style="flex:0 1 auto; min-width:0;"><img src="https://huggingface.co/AtomicChat/Laguna-S-2.1-NVFP4/resolve/main/pill_atomic_v3.png" alt="Atomic Chat" style="width:100%; height:auto; max-width:186px;"></a>
<a href="https://discord.gg/8wGSsvmg4V" style="flex:0 1 auto; min-width:0;"><img src="https://huggingface.co/AtomicChat/Laguna-S-2.1-NVFP4/resolve/main/pill_discord_v3.png" alt="Join Discord" style="width:100%; height:auto; max-width:184px;"></a>
<a href="https://github.com/AtomicBot-ai/Atomic-Chat" style="flex:0 1 auto; min-width:0;"><img src="https://huggingface.co/AtomicChat/Laguna-S-2.1-NVFP4/resolve/main/pill_github_v3.png" alt="GitHub" style="width:100%; height:auto; max-width:141px;"></a>
</div>
<br/>
<img src="https://huggingface.co/AtomicChat/Laguna-S-2.1-NVFP4/resolve/main/hero.png" alt="Laguna S 2.1" style="width:100%; max-width:100%; height:auto; margin-bottom:0.6em;"/>
<div style="display:flex; justify-content:center; gap:0.5em;">
<a href="https://huggingface.co/poolside/Laguna-S-2.1"><strong>Base model: poolside/Laguna-S-2.1</strong></a>
</div>
</center>
Laguna S 2.1, self-quantized to NVFP4 by Atomic Chat. Built straight from Poolside's original weights with a per-tensor importance matrix, so this is not a repack of somebody else's files. Runs fully offline.
Highlights
- 117.6B parameters: the weights this repo quantizes.
- Context length: 1,048,576 tokens (1M), as published by Poolside.
- 48 layers: Mixture-of-Experts, hybrid sliding-window (512) and global attention.
- Full imatrix ladder: every quant is calibrated with an importance matrix.
- 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.
- 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.
[!NOTE] These NVFP4s are self-quantized from the original weights, not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.
Model Overview
| Property | Value |
|---|---|
| Base model | poolside/Laguna-S-2.1 |
| Parameters | 117.6B |
| Layers | 48 |
| Experts | 256 routed (top-10) |
| Sliding window | 512 tokens |
| Context length | 1,048,576 tokens (1M) |
| Vocabulary | 100,352 |
| Modalities | Text |
| Architecture | Mixture-of-Experts, 256 experts (top-10), hybrid sliding-window (512) and global attention, 48 attention heads over 8 KV heads, LagunaForCausalLM |
| This repo | NVFP4 weights |
Benchmarks
| Benchmark | Score |
|---|---|
| Laguna S 2.1 | 70.2% |
| Tencent Hy3 | 71.7% |
| Inkling | 63.8% |
| Nemotron 3 Ultra | 56.4% |
| DeepSeek-V4-Pro Max | 64.0% |
| Kimi K3 | 88.3% |
| Qwen 3.7 Max | 74.5% |
| Muse Spark 1.1 | 80% |
| Claude Fable 5 | 88% |
Scores are Poolside's published results for the base poolside/Laguna-S-2.1, not our own measurements. Quantization preserves the large majority of this; Q4_K_M and up stay close to full precision.
Get started
- Atomic Chat: search
AtomicChat/Laguna-S-2.1-NVFP4and hit Use this model. - vLLM:
vllm serve AtomicChat/Laguna-S-2.1-NVFP4 --max-model-len 8192
Best practices
| Parameter | Value |
|---|---|
| temperature | 1.0 |
| top_p | 1.0 |
| top_k | 20 |
| min_p | 0.0 |
Poolside's recommended sampling configuration for poolside/Laguna-S-2.1.
How these were made
- Download
poolside/Laguna-S-2.1(original weights). - Quantize to NVFP4 with
llm-compressorover a calibration corpus.
License
Original model by Poolside, released under the OpenMDW-1.1 license. Full terms: OpenMDW-1.1. Quantized by Atomic Chat.
- Task
- Text Generation
- Library
- transformers
- Type
- laguna
- License
- openmdw-1.1
- Created
- Jul 22, 2026
- Updated
- Jul 22, 2026