Instructions to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="poolside-laguna-hackathon/Laguna-XS.2-GGUF",
	filename="Laguna-XS.2-F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

Use Docker

docker model run hf.co/poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

LM Studio
Jan

vLLM

How to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "poolside-laguna-hackathon/Laguna-XS.2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "poolside-laguna-hackathon/Laguna-XS.2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

Ollama
How to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with Ollama:
```
ollama run hf.co/poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
```

Unsloth Studio

How to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for poolside-laguna-hackathon/Laguna-XS.2-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for poolside-laguna-hackathon/Laguna-XS.2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for poolside-laguna-hackathon/Laguna-XS.2-GGUF to start chatting

Docker Model Runner
How to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with Docker Model Runner:
```
docker model run hf.co/poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16
```

Lemonade

How to use poolside-laguna-hackathon/Laguna-XS.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull poolside-laguna-hackathon/Laguna-XS.2-GGUF:F16

Run and chat with the model

lemonade run user.Laguna-XS.2-GGUF-F16

List all available models

lemonade list

Laguna XS.2 - GGUF Quantizations

First-ever GGUF conversion of poolside/Laguna-XS.2, produced as part of the Poolside Research Hackathon.

Laguna XS.2 is a 33.4B total parameter (3B activated) Mixture-of-Experts model built for long-horizon agentic coding. These GGUF files enable local deployment via llama.cpp and compatible inference engines.

⚠️ Inference status: Full CPU/GPU inference requires 6 C++ patches to llama-model.cpp (documented below). All benchmarks were run using vLLM on the original BF16 checkpoint.

Available Files

Filename	Quant	Size	Notes
Laguna-XS.2-F16.gguf	F16	63 GB	Fixed source (experts F16, attention F16)
Laguna-XS.2-Q4_K_M.gguf	Q4_K_M	~60 GB	Attention Q4, experts F16

Note on quantization sizes: llama.cpp does not quantize 3D MoE expert tensors. Attention/embedding weights are fully quantized; expert weights remain F16. This is a known llama.cpp limitation for large MoE models. Proper small quants (~18GB Q4_K_M) require upstream llama.cpp changes.

Benchmark Results

All benchmarks: H200 MIG 71GB, vLLM 0.21.0, BF16, temperature=0.

Benchmark	Score	Details
HumanEval pass@1	90.2% (148/164)	thinking=off
GPQA Diamond	42.6% (84/197)	thinking=on, +17.6% above random
MATH500	46.6% (233/500)	full 500 problems, thinking=on

MATH500 by Subject

Subject	Score
Algebra	69.4%
Prealgebra	65.9%
Number Theory	54.8%
Counting & Probability	36.8%
Geometry	31.7%
Precalculus	21.4%
Intermediate Algebra	20.6%

Throughput (BF16, vLLM, H200 71GB)

Mode	tok/s
Single request	57–74
5 concurrent	100–106

Benchmark Visualizations

Architecture - Key Differences from Mixtral

Feature	Laguna XS.2	Mixtral
Routing	Sigmoid	Softmax
Shared expert	Yes (always runs)	No
Routed scaling	2.5×	1.0×
Attention	Interleaved SWA/GA 3:1	Global only
RoPE θ	500k (GA) / 10k (SWA)	Single value
Per-head gating	Softplus g_proj	None
Expert count	256, top-8	8, top-2
Q-heads per layer	48 (GA) / 64 (SWA)	Uniform

Custom GGUF Metadata Keys

Key	Value
`laguna.attention.layer_types`	`[0,1,1,1,0,...]` — GA=0, SWA=1
`laguna.attention.heads_per_layer`	`[48,64,64,64,48,...]`
`laguna.rope.theta_swa`	`10000.0`
`laguna.rope.partial_rotary_factor`	`0.5`
`laguna.moe.routed_scaling_factor`	`2.5`
`laguna.moe.sigmoid_routing`	`true`
`laguna.attention.softplus_gating`	`true`

C++ Patches for llama.cpp Inference

Sigmoid routing: ggml_soft_max → ggml_sigmoid in MoE router
Routed scaling: multiply routed output by laguna.moe.routed_scaling_factor (2.5)
e_score_correction_bias: add to router scores before top-k
Dual RoPE θ: use laguna.rope.theta_swa for SWA layers
Partial RoPE: rotate only 50% of head_dim on GA layers
Softplus g_proj gating: softplus(g_proj(x)) per head after attention, before o_proj

Conversion

Registration in conversion/__init__.py:

"LagunaForCausalLM": "laguna"

The conversion script (conversion/laguna.py) handles:

Stacking 256 individual expert weights → 3D tensors [256, dim_in, dim_out]
Per-layer variable Q-heads (48 GA / 64 SWA)
Sigmoid router, shared expert, g_proj, e_score_correction_bias
All Laguna metadata as custom GGUF keys

Original Model

Model: poolside/Laguna-XS.2
License: Apache 2.0
Paper: Technical Report

Produced by Saurabh Mallik for the Poolside Research Hackathon.

Downloads last month: 193

GGUF

Model size

33B params

Architecture

qwen2moe

Hardware compatibility

4-bit

16-bit

Model tree for poolside-laguna-hackathon/Laguna-XS.2-GGUF

Base model

poolside/Laguna-XS.2

Quantized

(16)

this model