Instructions to use YTan2000/Laguna-XS-2.1-TQ3_4S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use YTan2000/Laguna-XS-2.1-TQ3_4S with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf YTan2000/Laguna-XS-2.1-TQ3_4S
# Run inference directly in the terminal:
llama cli -hf YTan2000/Laguna-XS-2.1-TQ3_4S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf YTan2000/Laguna-XS-2.1-TQ3_4S
# Run inference directly in the terminal:
llama cli -hf YTan2000/Laguna-XS-2.1-TQ3_4S

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 YTan2000/Laguna-XS-2.1-TQ3_4S
# Run inference directly in the terminal:
./llama-cli -hf YTan2000/Laguna-XS-2.1-TQ3_4S

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 YTan2000/Laguna-XS-2.1-TQ3_4S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf YTan2000/Laguna-XS-2.1-TQ3_4S

Use Docker

docker model run hf.co/YTan2000/Laguna-XS-2.1-TQ3_4S

LM Studio
Jan

vLLM

How to use YTan2000/Laguna-XS-2.1-TQ3_4S with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YTan2000/Laguna-XS-2.1-TQ3_4S"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YTan2000/Laguna-XS-2.1-TQ3_4S",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YTan2000/Laguna-XS-2.1-TQ3_4S

Ollama
How to use YTan2000/Laguna-XS-2.1-TQ3_4S with Ollama:
```
ollama run hf.co/YTan2000/Laguna-XS-2.1-TQ3_4S
```

Unsloth Studio

How to use YTan2000/Laguna-XS-2.1-TQ3_4S 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 YTan2000/Laguna-XS-2.1-TQ3_4S 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 YTan2000/Laguna-XS-2.1-TQ3_4S to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for YTan2000/Laguna-XS-2.1-TQ3_4S to start chatting

How to use YTan2000/Laguna-XS-2.1-TQ3_4S with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Laguna-XS-2.1-TQ3_4S

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "YTan2000/Laguna-XS-2.1-TQ3_4S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use YTan2000/Laguna-XS-2.1-TQ3_4S with Docker Model Runner:
```
docker model run hf.co/YTan2000/Laguna-XS-2.1-TQ3_4S
```

Lemonade

How to use YTan2000/Laguna-XS-2.1-TQ3_4S with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull YTan2000/Laguna-XS-2.1-TQ3_4S

Run and chat with the model

lemonade run user.Laguna-XS-2.1-TQ3_4S-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use YTan2000/Laguna-XS-2.1-TQ3_4S with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Laguna-XS-2.1-TQ3_4S

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 YTan2000/Laguna-XS-2.1-TQ3_4S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use YTan2000/Laguna-XS-2.1-TQ3_4S with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf YTan2000/Laguna-XS-2.1-TQ3_4S

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "YTan2000/Laguna-XS-2.1-TQ3_4S" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

TurboLaguna-XS

Canonical artifact: Laguna-XS-2.1-TQ3_4S

TurboLaguna-XS is the TurboQuant GGUF build of Poolside's Laguna XS 2.1 — a sigmoid-routed mixture-of-experts coding model with 256 experts per layer, a shared expert, QK-norm, and hybrid YaRN/sliding-window RoPE.

The exact file and runtime artifact name is:

Laguna-XS-2.1-TQ3_4S.gguf

Required Runtime

This model uses the custom TQ3_4S tensor type. Stock llama.cpp builds cannot load it. You must use the TurboQuant runtime fork:

turbo-tan/llama.cpp-tq3

This is a standard (non-MTP) model — no draft-MTP flags are needed.

Parent Model

Upstream parent: poolside/Laguna-XS-2.1-GGUF
Source quant: Laguna-XS-2.1-BF16.gguf (63.8 GB, 16.01 bpw)
Format conversion and TurboQuant packaging: turbo-tan/llama.cpp-tq3

Files

File	Size	Notes
`Laguna-XS-2.1-TQ3_4S.gguf`	16 GB (4.05 bpw)	Main model — 678 tensors, 40 layers × 256 routed experts
`thumbnail.png`	—	Model card image
`benchmark.png`	—	Benchmark summary

Quantization Recipe

Quantized from the official BF16 GGUF using the standard TQ3_4S recipe:

./build/bin/llama-quantize --allow-requantize \
  --output-tensor-type q6_K \
  --token-embedding-type q6_K \
  Laguna-XS-2.1-BF16.gguf \
  Laguna-XS-2.1-TQ3_4S.gguf \
  TQ3_4S

Tensor policy:

Routed experts, attention projections, shared experts → tq3_4s (4.0 bpw)
Token embeddings, output head → q6_K
Norms, gates, biases → f32 (untouched)

Result: 63.8 GB → 16 GB (3.98× compression), 42% smaller than Poolside's own Q4_K_M (20 GB).

Recommended Runtime

./build/bin/llama-server \
  -m Laguna-XS-2.1-TQ3_4S.gguf \
  --host 127.0.0.1 --port 8080 \
  -c 8192 -np 1 -ngl 99 -fa on \
  --reasoning off --jinja

Build note:

-fa on is the runtime flash-attention flag, not the CMake GGML_CUDA_FA_ALL_QUANTS build flag.

GPU Memory Profiles

GPU memory	Suggested context	KV cache	Notes
16 GiB	`4096`	`-ctk q4_0 -ctv tq3_0`	Tight fit — keep context small
24 GiB	`8192` to `32768`	`-ctk q8_0 -ctv tq3_0`	Validated desktop profile
128 GiB GB10	`65536+`	`-ctk q4_0 -ctv tq3_0`	Full headroom for long context

Tested Hardware

NVIDIA RTX 3090 24 GB — primary validation platform
llama.cpp-tq3 fork, branch feat/laguna-arch (Laguna arch from upstream ggml-org/llama.cpp#25165)

Benchmarks

All scores: greedy decoding, reasoning off, -ngl 99 -fa on, RTX 3090.

Benchmark	Score	tok/s
HumanEval (base)	0.805	196
HumanEval+ (extra tests)	0.762	196
MBPP (base)	0.833	199
MBPP+ (extra tests)	0.720	199
Hard86 (20 tasks / 86 assertions)	64.0% (55/86)	202
BenchLoop coding	100.0 (12/12)	—
BenchLoop overall	73.7	—
BenchLoop speed	96.4 (9/9)	—

Comparison (all TQ3_4S, same RTX 3090)

Model	HE+	MBPP+	Hard86	Coding	tok/s	Size
Laguna XS 2.1	0.762	0.720	64.0%	100.0	196	16 GB
Qwen3.5 9B	0.671	0.563	44.2%	79.2	134	4.5 GB
Qwen3.6 27B MTP	0.927	0.878	—	100.0	42–54	12.9 GB

Laguna XS is a coding specialist: perfect BenchLoop coding (same as the 27B), +19.8pp Hard86 over the 9B, at 3.6–4.6× the 27B's decode speed.

Validation

llama-simple-chat coherence smoke: PASS
llama-server --reasoning off strict smoke: PASS (content = "ok")
llama-bench pp2048: 745 tok/s
llama-bench tg128: 196 tok/s
evalplus HE/HE+/MBPP/MBPP+: scored (see above)
hard86: 55/86
benchloop v0.2.3: overall 73.7