Instructions to use linuxid10t/Laguna-XS.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use linuxid10t/Laguna-XS.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="linuxid10t/Laguna-XS.2-GGUF",
	filename="Laguna-XS.2-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use linuxid10t/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 linuxid10t/Laguna-XS.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf linuxid10t/Laguna-XS.2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf linuxid10t/Laguna-XS.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf linuxid10t/Laguna-XS.2-GGUF:Q4_K_M

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 linuxid10t/Laguna-XS.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf linuxid10t/Laguna-XS.2-GGUF:Q4_K_M

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 linuxid10t/Laguna-XS.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf linuxid10t/Laguna-XS.2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/linuxid10t/Laguna-XS.2-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use linuxid10t/Laguna-XS.2-GGUF with Ollama:
```
ollama run hf.co/linuxid10t/Laguna-XS.2-GGUF:Q4_K_M
```

Unsloth Studio new

How to use linuxid10t/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 linuxid10t/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 linuxid10t/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 linuxid10t/Laguna-XS.2-GGUF to start chatting

Pi new

How to use linuxid10t/Laguna-XS.2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf linuxid10t/Laguna-XS.2-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "linuxid10t/Laguna-XS.2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use linuxid10t/Laguna-XS.2-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf linuxid10t/Laguna-XS.2-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default linuxid10t/Laguna-XS.2-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use linuxid10t/Laguna-XS.2-GGUF with Docker Model Runner:
```
docker model run hf.co/linuxid10t/Laguna-XS.2-GGUF:Q4_K_M
```

Lemonade

How to use linuxid10t/Laguna-XS.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull linuxid10t/Laguna-XS.2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Laguna-XS.2-GGUF-Q4_K_M

List all available models

lemonade list

Laguna-XS.2 GGUF

GGUF quantizations of poolside/Laguna-XS.2. Converted and tested with a patched fork of llama.cpp that implements LLM_ARCH_LAGUNA from scratch.

Requires the custom fork. Upstream llama.cpp does not support this architecture. Fork: https://github.com/linuxid10t/llama.cpp-add-laguna

Files

File	Quant	Size	Notes
`Laguna-XS.2-f16.gguf`	f16	~67 GB	Full precision, reference
`Laguna-XS.2-Q4_K_M.gguf`	Q4_K_M	~20 GB	Recommended for most users

Usage

git clone https://github.com/linuxid10t/llama.cpp-add-laguna
cd llama.cpp-add-laguna && cmake -B build && cmake --build build -j$(nproc)

./build/bin/llama-cli \
  -m Laguna-XS.2-Q4_K_M.gguf \
  --ctx-size 131072 \
  --temp 0 \
  -p "The capital of France is"

Chat / thinking mode

# Thinking on (default) — model prefills <think> and generates a reasoning trace
./build/bin/llama-cli -m Laguna-XS.2-Q4_K_M.gguf -cnv --ctx-size 32768

# Thinking off — direct answer, no reasoning trace
./build/bin/llama-cli -m Laguna-XS.2-Q4_K_M.gguf -cnv --ctx-size 32768 --reasoning off

The chat template, thinking-mode prefix, EOT token (</assistant>, token 24), and streaming parser are all handled automatically — no manual prompt engineering needed.

Architecture

Property	Value
Parameters	33B total, ~3B active per token
Layers	40 (10 global + 30 SWA, 3:1 pattern)
Attention heads	64 (global layers) / 48 (SWA layers)
KV heads	8 (GQA)
Q/K norm	RMSNorm per head
Attention gate	Head-wise softplus gate on `o_proj` input, SWA layers only
SWA window	512 tokens
Experts	256 routed (top-8) + 1 shared
Dense layers	Layer 0 only
MoE router	Sigmoid + `e_score_correction_bias` (added at selection, not routing)
Routing scale	`moe_routed_scaling_factor` with weight normalization
Global RoPE	YaRN: base 500K, factor 32, original_max 4096, β_fast 64, β_slow 1, partial_rotary 0.5
SWA RoPE	Default: base 10K, full rotary
Context length	131,072 tokens

Implementation Notes

Attention gate: SWA layers have an extra self_attn.g_proj that produces a per-head scalar. This is applied as a softplus gate to the SDPA output before o_proj. Global layers have no gate.

Partial rotary: Global layers rotate only the first half of head dimensions (matching partial_rotary_factor=0.5). SWA layers use full rotary. This is handled via llama.cpp's existing n_rot_full / 2 mechanism.

Dual RoPE: Global and SWA layers use entirely different RoPE configs. The fork adds per-layer-type YaRN siblings to llama_hparams / llama_cparams and selects at graph build time via hparams.is_swa(il).

MoE routing: Router logits pass through sigmoid (not softmax), biased by a per-expert e_score_correction_bias that is added only during top-k selection, not during weight computation. Routing weights are L1-normalized before scaling by moe_routed_scaling_factor.

Thinking mode prefill: The chat template injects <think> as the generation prompt prefix when thinking is enabled. The streaming parser is patched to treat this as a delimiter-style boundary (not a generated token), so the <think> tag never appears in streaming output.

Stop token: </assistant> is token 24, a regular vocabulary token (not a special token). The fork adds it to antiprompt so the stop-word erase logic strips it before output.

Tested

Greedy decode on "The capital of France is" → " Paris.\nThe capital of Germany is" ✓
10K-token prompt (exercises SWA layers) — no corruption ✓
35K needle-in-haystack (SWORDFISH99) — correctly retrieved (exercises global YaRN layers) ✓

Known Limitations

Numerical validation against HF Transformers not yet done (requires CUDA/ROCm).
Q4_K_M vs f16 top-1 token agreement not formally checked (f16 GGUF exceeds available RAM for full eval).

Downloads last month: 116

GGUF

Model size

33B params

Architecture

laguna

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for linuxid10t/Laguna-XS.2-GGUF

Base model

poolside/Laguna-XS.2

Quantized

(14)

this model