poolside / text-generation updated 5 days ago

Laguna-S-2.1-NVFP4

Name: Laguna-S-2.1-NVFP4
Author: poolside

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.

Params

117.6 B

Context

1,048,576

Downloads 30d

386 K

Likes

172

Licence: openmdw-1.1 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

386 K181 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	u8	99.7 GB	127.8 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 1024K ctx	99.7 GB	2,367.3 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/laguna-s-2-1-nvfp4
{
  "hf_id": "poolside/Laguna-S-2.1-NVFP4",
  "params_b": 117.56,
  "context_length": 1048576,
  "license": { "id": "openmdw-1.1", "commercial": "unknown" },
  "downloads_30d": 385829,
  "vram_estimates": [
    { "quant": "u8", "gb": 127.8 }
  ],
  "updated_at": "2026-08-02T01:00:24Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: LagunaForCausalLM
Parameters: 117.6 B
Tensor type: U8
Context length: 1,048,576
Vocabulary: 100,352
Layers / heads: 48 / 48
Licence: openmdw-1.1
First seen on the Hub: 2026-07-02
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-32B 8.3 M dolphin-2.9.1-yi-1.5-34b 4.6 M gpt-oss-120b 4.2 M NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 2.8 M DeepSeek-V4-Flash 2.7 M Qwen3-Coder-Next-FP8 2.2 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB