RedHatAI

Laguna-XS.2-FP8

Deploy Dedicated

README

License: apache-2.0

Highlights

Mixed SWA and global attention layout: Laguna XS.2 uses sigmoid gating with per-layer rotary scales, enabling mixed SWA (Sliding Window Attention) and global attention layers in a 3:1 ratio (across 40 total layers)
KV cache in FP8: KV cache quantized to FP8, reducing memory per token
Native reasoning support: Interleaved thinking between tool calls with support for enabling and disabling thinking per-request
Local-ready: At 33B total parameters and 3B activated, Laguna XS.2 is compact enough to run on a Mac with 36 GB of RAM. Available on Ollama
Apache 2.0 license: Use and modify freely for commercial and non-commercial purposes

Model overview

Training: pre-training, post-training and reinforcement learning stages
Number of parameters: 33B total with 3B activated per token
Optimizer: Muon
Layers: 40 layers (10 layers with global attention, 30 layers with sliding window attention)
Experts: 256 experts with 1 shared expert
Sliding Window: 512 tokens
Modality: text-to-text
Context window: 131,072 tokens
Reasoning support: interleaved thinking with preserved thinking

Benchmark results

Table with columns: Model, Size (total params.), SWE-bench Verified, SWE-bench Multilingual, SWE-bench Pro (Public Dataset), Terminal-Bench 2.0
Model	Size (total params.)	SWE-bench Verified	SWE-bench Multilingual	SWE-bench Pro (Public Dataset)	Terminal-Bench 2.0
Laguna XS.2 (BF16)	33B	68.2%	62.4%	44.5%	30.1%
Devstral Small 2	24B dense	68.0%	55.7%	-	22.5%
Gemma 4 31B IT

We used the highest publicly-referenced scores for all comparison models across each benchmark. In almost all cases these were official scores published in release blog posts or equivalent, with the exception of Gemma 4 31B IT where the highest published scores were reported by the Qwen team and Claude Haiku 4.5 where the highest published (verified) scores for SWE-bench Pro and Terminal-Bench 2.0 are from their respective official leaderboards.

All benchmarking for Laguna XS.2 was completed using the Laude Institute’s Harbor Framework with our agent harness, using a maximum of 500 steps and sandboxed execution using 8 GB RAM/2 CPUs (with the exception of Terminal-Bench 2.0; see below). The same sampling parameters were used for all benchmarking: temperature=0.7 and top_k=20. Some base task images and verifiers were patched to fix infrastructure reliability issues inherent in task setup, such as rate limits on third-party dependencies in external registries used by the verifier. More details outlining these updates and other findings will follow in a future technical blog post.

SWE-bench Verified: mean pass@1 averaged over 4 runs.
SWE-bench Multilingual: mean pass@1 averaged over 7 runs.
SWE-bench Pro: mean pass@1 averaged over 3 runs.
Terminal-Bench 2.0: mean pass@1 averaged over 5 runs. 48GB RAM/32 CPUs.

Usage

Laguna XS.2 has launch-day support in vLLM and Transformers, and TRT-LLM thanks to the support of the team at NVIDIA.

The fastest way to get started is with our API, directly or using OpenRouter.

[!NOTE] For complete usage instructions, see the main Laguna XS.2 model card.

Local deployment

Laguna XS.2 is supported in vLLM and Transformers, and TRT-LLM thanks to the support of the team at NVIDIA. Use Laguna-XS.2 with Ollama (with MLX support) and the mlx-lm framework for the best experience on your local machine.

vLLM

The full vLLM recipe is on the main Laguna XS.2 model card and on the vLLM recipes page. Quantization is detected automatically from quantization_config in this checkpoint, so the same command works with poolside/Laguna-XS.2-FP8 substituted for the model ID. No extra flags required.

[!NOTE] Please note that, during testing, we discovered that models with FP8-quantised KV caches can produce scrambled output when deployed on non-Hopper GPUs. We are actively investigating this issue with the vLLM team, but in the meantime, you can circumvent this issue by explicitly disabling FP8 KV cache (Laguna XS.2 has 40 layers, so list every layer in --kv-cache-dtype-skip-layers):

shell
VLLM_USE_DEEP_GEMM=0 vllm serve \
    --model poolside/Laguna-XS.2-FP8 \
    --tool-call-parser poolside_v1 \
    --reasoning-parser poolside_v1 \
    --enable-auto-tool-choice \
    --served-model-name laguna \
    --default-chat-template-kwargs '{"enable_thinking": true}' \
    --kv-cache-dtype-skip-layers $(seq 0 39) \
    --moe_backend marlin

The BF16 checkpoint is unaffected as it does not declare an FP8 KV cache.

Transformers

The full Transformers recipe is on the main Laguna XS.2 model card. Substitute poolside/Laguna-XS.2-FP8 for the model ID; quantization is detected automatically from quantization_config.

TRT-LLM

[!NOTE] Requires building TensorRT-LLM from the upstream PR that adds Laguna XS.2 support (NVIDIA/TensorRT-LLM#13559). Once that PR merges, the same code will work on a released tensorrt-llm wheel.

The full TRT-LLM recipe, including the laguna_minimal_overlay.sh step needed for transformers 4.57 compatibility, is on the main Laguna XS.2 model card. Quantization is detected automatically from quantization_config in this checkpoint, so no extra flags are required:

python
from tensorrt_llm import LLM

# OVERLAY built from poolside/Laguna-XS.2-FP8 via laguna_minimal_overlay.sh
llm = LLM(model=OVERLAY, trust_remote_code=True)

Ollama

Visit Ollama's model library to pull to your local machine.

Controlling reasoning

Laguna XS.2 has native reasoning support and is designed to work best with preserved thinking, where reasoning content from prior assistant messages is preserved in the message history. This model will generally reason before calling tools and between tool calls.

python
import json
from openai import OpenAI

client = OpenAI(
  base_url="https://inference.poolside.ai/v1",
  api_key="...",
)

model = "poolside/laguna-xs.2"

tools = [{"type": "function", "function": {
  "name": "shell",
  "description": "Execute a bash command and return the output.",
  "parameters": {"type": "object", "properties": {"cmd": {"type": "string"}}, "required": ["cmd"]},
}}]

messages = [
  {"role": "system", "content": "You are a coding agent with access to a shell tool."},
  {"role": "user", "content": "Run uname -a"},
]

# Thinking is enabled by default when the server sets --default-chat-template-kwargs {"enable_thinking": True}
# When using the Poolside API (https://inference.poolside.ai/v1), this flag is set by default
response = client.chat.completions.create(
  model=model,
  messages=messages,
  tools=tools,
  stream=True,
)

reasoning, content, tool_calls = "", "", []
for chunk in response:
  delta = chunk.choices[0].delta
  if hasattr(delta, "reasoning_content") and delta.reasoning_content:
    reasoning += delta.reasoning_content
  if hasattr(delta, "content") and delta.content:
    content += delta.content
  if hasattr(delta, "tool_calls") and delta.tool_calls:
    for tc in delta.tool_calls:
      if tc.index >= len(tool_calls):
        tool_calls.append({"id": tc.id, "function": {"name": "", "arguments": ""}})
      if tc.function.name:
        tool_calls[tc.index]["function"]["name"] = tc.function.name
      if tc.function.arguments:
        tool_calls[tc.index]["function"]["arguments"] += tc.function.arguments

print(f"Reasoning: {reasoning}\nContent: {content}\nTool calls: {tool_calls}\n")

# Return reasoning in the next request for best performance
messages.append({
  "role": "assistant",
  "content": content,
  "reasoning_content": reasoning,
  "tool_calls": [{"id": tc["id"], "type": "function", "function": tc["function"]} for tc in tool_calls]
})

messages.append({
  "role": "tool",
  "tool_call_id": tool_calls[0]["id"],
  "content": json.dumps({"stdout": "Darwin arm64", "exit_code": "0"})
})

response = client.chat.completions.create(
  model=model,
  messages=messages,
  tools=tools,
  stream=True,
)

reasoning, content = "", ""
for chunk in response:
  delta = chunk.choices[0].delta
  if hasattr(delta, "reasoning_content") and delta.reasoning_content:
    reasoning += delta.reasoning_content
  if hasattr(delta, "content") and delta.content:
    content += delta.content

print(f"Reasoning: {reasoning}\nContent: {content}")

Disabling reasoning

You can disable thinking by setting enable_thinking to False in a request or by not providing --default-chat-template-kwargs {"enable_thinking": True} or equivalent when starting the server.

python
from openai import OpenAI
client = OpenAI()

completion = client.chat.completions.create(
  model="poolside/laguna-xs.2",
  messages=[
    {"role": "user", "content": "Write a retry wrapper with exponential backoff."}
  ],
  extra_body={
    "chat_template_kwargs": { "enable_thinking": False },
  },
  stream=True
)

for chunk in completion:
    print(chunk.choices[0].delta)

For agentic coding use cases, we recommend enabling thinking and preserving reasoning in message history as outlined in the [Controlling reasoning] section.

License

This model is licensed under the Apache 2.0 License.

Intended and Responsible Use

Laguna XS.2-FP8 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna XS.2-FP8 is subject to the Apache 2.0 License, and should be used consistently with Poolside's Acceptable Use Policy. We advise against circumventing Laguna XS.2-FP8 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.

Please report security vulnerabilities or safety concerns to security@poolside.ai.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider