unsloth / text-generation updated 1 week ago

Laguna-S-2.1-GGUF

Name: Laguna-S-2.1-GGUF
Author: unsloth

To run or train any LLM with a open-source UI, install Unsloth Studio via: bash curl -fsSL https://unsloth.ai/install.sh sh powershell irm https://unsloth.ai/install.ps1 iex

Params

—

Context

—

Downloads 30d

182 K

Likes

284

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

Download history

daily snapshots · 7 days

182 K159 K

Jul 31Aug 2Aug 4Aug 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
Laguna-S-2.1-UD-IQ1_S.gguf	IQ1_S	33.8 GB	37.6 GB	❌ Won’t fit
Laguna-S-2.1-UD-IQ1_M.gguf	IQ1_M	35.6 GB	39.7 GB	❌ Won’t fit
Laguna-S-2.1-UD-IQ2_XXS.gguf	IQ2_XXS	37.2 GB	41.4 GB	❌ Won’t fit
Laguna-S-2.1-UD-IQ2_M.gguf	IQ2_M	37.3 GB	41.5 GB	❌ Won’t fit
Laguna-S-2.1-UD-Q2_K_XL.gguf	Q2_K_XL	39.7 GB	44.2 GB	❌ Won’t fit
Laguna-S-2.1-UD-IQ3_XXS.gguf	IQ3_XXS	44.3 GB	49.2 GB	❌ Won’t fit
Laguna-S-2.1-UD-IQ3_S.gguf	IQ3_S	48.4 GB	53.8 GB	❌ Won’t fit
Laguna-S-2.1-BF16-00001-of-00005.gguf	GGUF	50.0 GB	55.5 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 · GGUF

$ ollama run laguna-s-2-1-gguf

# pin the quantization explicitly
$ ollama run laguna-s-2-1-gguf-gguf

est. VRAM 55.5 GBon RTX 4090 · 24 GBJSON API →

Specifications

Licence: openmdw-1.1
First seen on the Hub: 2026-07-21
Training datasets: undisclosed
Added to our catalog: 2026-07-31

Appears in

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