AtomicChat

Laguna-S-2.1-NVFP4

README

License: openmdw-1.1

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

Table with columns: Property, Value
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`

Benchmarks

Table with columns: Benchmark, Score
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-NVFP4 and hit Use this model.
vLLM: vllm serve AtomicChat/Laguna-S-2.1-NVFP4 --max-model-len 8192

Best practices

Table with columns: Parameter, Value
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-compressor over a calibration corpus.

License

Original model by Poolside, released under the OpenMDW-1.1 license. Full terms: OpenMDW-1.1. Quantized by Atomic Chat.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

AtomicChat

Model Tree

Base

poolside/Laguna-S-2.1

Quantized

this model

Input Modalities

Text

Output Modalities