poolside / text-generation Open weights updated 3 months ago

Laguna-M.1

Name: Laguna-M.1
Author: poolside

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.

Params

225.8 B

Context

262,144

Downloads 30d

568 K

Likes

149

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 20 days

568 K199 K

Oct 4Oct 10Oct 17Oct 23

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	bf16	451.6 GB	531.1 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 256K ctx	451.6 GB	1,581.1 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-m-1
{
  "hf_id": "poolside/Laguna-M.1",
  "params_b": 225.80,
  "context_length": 262144,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 568241,
  "vram_estimates": [
    { "quant": "bf16", "gb": 531.1 }
  ],
  "updated_at": "2026-10-04T01:00:12Z"
}

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

Specifications

Architecture: LagunaForCausalLM
Parameters: 225.8 B
Tensor type: BF16
Context length: 262,144
Vocabulary: 100,352
Layers / heads: 70 / 64
Licence: apache-2.0
First seen on the Hub: 2026-06-15
Training datasets: undisclosed
Added to our catalog: 2026-10-04

Compare with any text-generation model

Popular comparisons

DeepSeek-V3.2 5.5 M DeepSeek-V4-Flash-0731 4.3 M gpt-oss-120b 3.0 M GLM-5.3-Flash-GGUF 892 K MiniMax-M2.5 859 K Hy3 798 K

Appears in

Trending text-generation