poolside / text-generation updated 1 month ago

Laguna-XS-2.1-NVFP4

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.

Params
33.4 B
Context
262,144
Downloads 30d
206 K
Likes
14
Licence: openmdw-1.1 Not gated SAFETENSORS View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (5 recorded)
206 K downloads in the last 30 days

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors u8 21.6 GB 29.3 GB ❌ Won’t fit
model.safetensors (bf16, full) bf16 + 256K ctx 21.6 GB 184.7 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-xs-2-1-nvfp4
{
  "hf_id": "poolside/Laguna-XS-2.1-NVFP4",
  "params_b": 33.44,
  "context_length": 262144,
  "license": { "id": "openmdw-1.1", "commercial": "unknown" },
  "downloads_30d": 205919,
  "vram_estimates": [
    { "quant": "u8", "gb": 29.3 }
  ],
  "updated_at": "2026-09-17T01:00:39Z"
}
est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture
LagunaForCausalLM
Parameters
33.4 B
Tensor type
U8
Context length
262,144
Vocabulary
100,352
Layers / heads
40 / 48
Licence
openmdw-1.1
First seen on the Hub
2026-06-20
Training datasets
undisclosed
Added to our catalog
2026-09-17
Compare with any text-generation model