poolside / text-generation updated 2 months ago

Laguna-XS-2.1-GGUF

Laguna XS 2.1 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. This model is an upgraded version of our Laguna XS.2 model with a +5.4% jump on SWE-bench Multilingual as well as stronger performance on terminal-style tasks.

Params
Context
Downloads 30d
235 K
Likes
93
Licence: openmdw-1.1 Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 23 days
238 K180 K
Aug 30Sep 6Sep 14Sep 21

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
Laguna-XS-2.1-Q4_K_M.gguf Q4_K_M 20.3 GB 22.8 GB ⚠️ Tight — reduce context
Laguna-XS-2.1-BF16.gguf GGUF 66.9 GB 74.1 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
~ · ollama · Q4_K_M
$ ollama run laguna-xs-2-1-gguf

# pin the quantization explicitly
$ ollama run laguna-xs-2-1-gguf-q4_k_m
est. VRAM 22.8 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence
openmdw-1.1
First seen on the Hub
2026-06-29
Training datasets
undisclosed
Added to our catalog
2026-08-30
Compare with any text-generation model