Instructions to use AxionML/Laguna-XS-2.1-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AxionML/Laguna-XS-2.1-NVFP4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AxionML/Laguna-XS-2.1-NVFP4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AxionML/Laguna-XS-2.1-NVFP4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("AxionML/Laguna-XS-2.1-NVFP4", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AxionML/Laguna-XS-2.1-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AxionML/Laguna-XS-2.1-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AxionML/Laguna-XS-2.1-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AxionML/Laguna-XS-2.1-NVFP4

SGLang

How to use AxionML/Laguna-XS-2.1-NVFP4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AxionML/Laguna-XS-2.1-NVFP4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AxionML/Laguna-XS-2.1-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AxionML/Laguna-XS-2.1-NVFP4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AxionML/Laguna-XS-2.1-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AxionML/Laguna-XS-2.1-NVFP4 with Docker Model Runner:
```
docker model run hf.co/AxionML/Laguna-XS-2.1-NVFP4
```

AxionML Laguna-XS-2.1-NVFP4

Mirrored by AxionML for open-source serving and deployment use cases. Part of AxionML's effort to provide ready-to-serve quantized models for the community.

Quantized by Poolside. The weights in this repository are an unmodified copy of poolside/Laguna-XS-2.1-NVFP4 (revision d32afde8b09af1539b49ff96ff5551c674485f8e). All credit for the quantization belongs to Poolside.

This is an NVFP4-quantized version of poolside/Laguna-XS-2.1 (33B total parameters, 3B activated), quantized with NVIDIA Model Optimizer.

About NVFP4 quantization: NVFP4 on Blackwell couples a compact E2M1 FP4 codebook with blockwise FP8 (E4M3) scaling over 16-element micro-blocks, so that 4-bit stored values remain numerically useful for neural-network computation. The E2M1 codebook provides a small, nonuniform set of representable magnitudes up to ±6 and relies on saturating behavior rather than IEEE NaN/Inf encodings to maximize usable range per bit. Using an FP8 block scale (rather than power-of-two-only E8M0) enables fractional scales and error-minimizing scale selection. On Blackwell Tensor Cores, native FP4 multipliers exploit E2M1 simplicity while higher-precision FP32 accumulation protects dot-product accuracy.

Ready for commercial and non-commercial use under OpenMDW-1.1 (included as LICENSE.md), consistent with Poolside's Acceptable Use Policy.

Model Summary


Architecture	MoE; 40 layers (10 global attention + 30 sliding-window), sigmoid-gated attention
Total Parameters	33B
Activated Parameters	3B
Context Length	262,144 tokens
Checkpoint Size	~22 GB

Evaluation Results

Benchmark	BF16	NVFP4
SWE-bench Verified	70.85 ± 0.85	68.95 ± 0.90
SWE-bench Multilingual	63.17 ± 1.42	61.83 ± 1.42
SWE-Bench Pro (Public)	47.61 ± 0.96	47.06 ± 0.96
Terminal-Bench 2.0	37.53 ± 2.81	37.08 ± 2.47

Scores reported by Poolside for this checkpoint (mean pass@1, Harbor framework).

Quantization Details

Quantization format: NVFP4 (compressed-tensors nvfp4-pack-quantized, group size 16) on routed and shared expert MLPs; Poolside's official NVFP4 release
KV cache: FP8 (static per-tensor)

Usage

Deploy with SGLang

python3 -m sglang.launch_server \
    --model-path AxionML/Laguna-XS-2.1-NVFP4 \
    --trust-remote-code

Deploy with vLLM

vllm serve AxionML/Laguna-XS-2.1-NVFP4 \
    --enable-auto-tool-choice \
    --tool-call-parser poolside_v1 \
    --reasoning-parser poolside_v1

Quantization is detected automatically in vLLM, SGLang (sgl-project/sglang#24204) and Transformers. The FP8 KV cache needs vLLM ≥ 0.22.0; tool calling needs a vLLM build with vllm#47311 (otherwise use --tool-call-parser glm47).

Limitations

The base model was trained on data that may contain toxic language and societal biases. The quantized model inherits these limitations. It may generate inaccurate, biased, or offensive content. Please refer to the original model card and the upstream quantized model card for full details.

Credits

Base model: poolside/Laguna-XS-2.1
Quantization: poolside/Laguna-XS-2.1-NVFP4 by Poolside
Mirror: AxionML

Downloads last month: 512

Safetensors

Model size

33B params

Tensor type

F32

BF16

Model tree for AxionML/Laguna-XS-2.1-NVFP4

Base model

poolside/Laguna-XS-2.1

Quantized

(41)

this model