Instructions to use llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF 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 llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-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 llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-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 llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M

Use Docker

docker model run hf.co/llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-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": "llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M

SGLang

How to use llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF 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 "llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF" \
    --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": "llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF",
		"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 "llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF" \
        --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": "llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF with Ollama:
```
ollama run hf.co/llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M
```
Unsloth Desktop

How to use llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M

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": "llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF with Docker Model Runner:
```
docker model run hf.co/llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M
```

Lemonade

How to use llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-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 llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M

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 "llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF:Q4_K_M" \
  --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"

🚨⚠️ I HAVE REACHED HUGGING FACE'S FREE STORAGE LIMIT ⚠️🚨

I can no longer upload new models unless I can cover the cost of additional storage.
I host 70+ free models as an independent contributor and this work is unpaid.
Without your support, no more new models can be uploaded.

☕ Ko-fi

Every contribution goes directly toward Hugging Face storage fees to keep models free for everyone.

94% fewer refusals (6/100 Uncensored vs 97/100 Original) while preserving model quality (0.0300 KL divergence).

❤️ Support My Work

Creating these models takes significant time, work and compute. If you find them useful consider supporting me:

Platform	Link	What you get
☕ Ko-fi	Coffee Tips	My eternal gratitude

Your help will motivate me and would go into further improving my workflow and coverings fees for storage, compute and may even help uncensoring bigger model with rental Cloud GPUs.

GGUF quantizations of llmfan46/Laguna-S-2.1-Uncensored-Heretic

This is a decensored version of poolside/Laguna-S-2.1, made using Heretic

Performance

Metric	This model	Original model (Qwen3-Coder-Next)
KL divergence	0.0300	0 (by definition)
Refusals	✅ 6/100	❌ 97/100

Lower refusals indicate fewer content restrictions, while lower KL divergence indicates more closeness to the original model's baseline. Higher refusals cause more rejections, objections, pushbacks, lecturing, censorship, softening and deflections.

Quantizations

Filename	Quant	Description
Laguna-S-2.1-Uncensored-Heretic-BF16.gguf	BF16	Full precision
Laguna-S-2.1-Uncensored-Heretic-Q8_0.gguf	Q8_0	Near-lossless, recommended
Laguna-S-2.1-Uncensored-Heretic-Q6_K.gguf	Q6_K	Excellent quality
Laguna-S-2.1-Uncensored-Heretic-Q5_K_M.gguf	Q5_K_M	Good balance
Laguna-S-2.1-Uncensored-Heretic-Q5_K_S.gguf	Q5_K_S	Smaller Q5
Laguna-S-2.1-Uncensored-Heretic-Q4_K_M.gguf	Q4_K_M	Good for limited VRAM
Laguna-S-2.1-Uncensored-Heretic-Q4_K_S.gguf	Q4_K_S	Smaller Q4
Laguna-S-2.1-Uncensored-Heretic-Q3_K_L.gguf	Q3_K_L	Low VRAM, decent quality
Laguna-S-2.1-Uncensored-Heretic-Q3_K_M.gguf	Q3_K_M	Low VRAM, smaller
Laguna-S-2.1-Uncensored-Heretic-Q3_K_S.gguf	Q3_K_S	Very Low VRAM
Laguna-S-2.1-Uncensored-Heretic-Q2_K.gguf	Q2_K	Very Very Low VRAM, only use if you have no other options

Vision Projector

Filename	Quant	Description
Laguna-S-2.1-Uncensored-Heretic-mmproj-BF16.gguf	BF16	Native precision
Laguna-S-2.1-Uncensored-Heretic-mmproj-F16.gguf	F16	F16 precision

A Vision Projector File is Required for vision/multimodal capabilities. Use alongside any quantization above.

Usage

Works with llama.cpp, LM Studio, Ollama, and other GGUF-compatible tools.

Vision support (experimental)

This repo includes two multimodal projector files built from numinousmuses/laguna-s-2.1-vision (frozen Qwen3-VL vision tower + a 35.4M-parameter trained projector, MIT — all credit to its author). Either works with any text quant in this repo; use F16 if your backend has trouble with BF16 (e.g. Vulkan or older builds):

llama-server -m Laguna-S-2.1-Uncensored-Heretic-Q6_K.gguf \
  --mmproj Laguna-S-2.1-Uncensored-Heretic-mmproj-BF16.gguf -ngl 99 --jinja

No extra flags or template overrides are needed — these GGUFs embed a chat template tuned for llama.cpp/LM Studio multimodal use (images are rendered before the question text, matching the projector's training order).

Vision works, but this is a grafted projector, not a natively-trained VLM — set your expectations:

Reliable: image attached in the first message of a conversation, short factual questions ("What does the sign say?", "What animal is this?"), low temperature (≤ 0.3) for vision turns.
Best-effort: images added mid-conversation. The model may answer tersely ("Answer: X"), misidentify the subject, or occasionally ignore the image — regenerate, or start a fresh chat with the image first for anything that matters.
Weak by design (per the upstream projector's training: 2,070 steps of short-form VQA, single-turn, no chat template): long detailed descriptions, trick/false-premise questions (hallucination-prone), and fine print — add --image-min-tokens 1024 for document images.
The projector was trained against stock Laguna-S-2.1; this repo pairs it with an abliterated backbone, so vision quality may sit slightly below the upstream author's published benchmarks.

Use on OpenRouter · Use on Vercel AI Gateway · Release blog post

Laguna S 2.1

Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token, designed for agentic coding and long-horizon work. It sits between Laguna XS 2.1 (33B-A3B) and Laguna M.1 (225B-A23B) in the Laguna series and shares the family recipe: a token-choice router with softplus gating over 256 routed experts plus one shared expert, grouped-query attention, and interleaved full/sliding-window attention.

Highlights

Mixed SWA and global attention layout: 48 layers in a 1:3 global-to-SWA ratio (12 global attention layers, 36 sliding-window layers, window 512), with softplus attention gating and per-layer-type rotary scales
1M context: 1,048,576-token context window
Native reasoning support: interleaved thinking between tool calls, with per-request control via enable_thinking
Speculative decoding: a trained DFlash draft model is available for lower-latency serving
Quantized variants: FP8, NVFP4, INT4 and GGUF
OpenMDW-1.1 license: Use and modify the model and associated materials freely for commercial and non-commercial purposes (learn more about OpenMDW)

Model overview

Number of parameters: 118B total, ~8B activated per token
Layers: 48 (12 global attention, 36 sliding-window attention)
Experts: 256 routed (top-10) plus 1 shared expert
Attention: grouped-query, 8 KV heads, head dim 128; per-head softplus output gating
Sliding window: 512 tokens
Context window: 1,048,576 tokens
Vocabulary: 100,352 tokens (Laguna family tokenizer)
Modality: text-to-text
Reasoning: interleaved thinking with preserved thinking

Benchmark results

benchmarks

Model	Size	Terminal-Bench 2.1	SWE-bench Multilingual	SWE-Bench Pro (Public Dataset)	DeepSWE	SWE Atlas (Codebase QnA)	Toolathlon Verified
Laguna S 2.1	118B-A8B	70.2%	78.5%	59.4%	40.4%	46.2%	49.7%
Tencent Hy3	295B-A21B	71.7%	75.8%	57.9%	-	-	-
Inkling	975B-A41B	63.8%	-	54.3%	-	-	45.5%*
Nemotron 3 Ultra	550B-A55B	56.4%	67.7%	-	-	-	34.3%*
DeepSeek-V4-Pro Max	1.6T-A49B	64.0%*	76.2%	55.4%	9.0%*	27.2%*	55.9%*
Kimi K3	2800B-A50B	88.3%	-	-	69%	-	-
Qwen 3.7 Max	-	74.5%*	78.3%	60.6%	-	-	-
Muse Spark 1.1	-	80%	-	61.5%	53.3%	42.2%*	75.6%
Claude Fable 5	-	88%	-	80.3%	70%	-	-

Benchmarks as of 21 July 2026. Laguna S 2.1 in bold; a dash (-) marks a benchmark a model was not evaluated on. Scores marked * are as reported by third parties: Terminal-Bench 2.1 and DeepSWE via Artificial Analysis, SWE Atlas via Scale AI's official leaderboard, and Toolathlon Verified via its official leaderboard. Full evaluation trajectories: trajectories.poolside.ai.

Usage

Laguna S 2.1 uses the same laguna architecture as Laguna XS 2.1, so the same engine integrations apply (vLLM, SGLang, Transformers, TRT-LLM, llama.cpp). At 118B parameters the BF16 checkpoint needs multiple GPUs (roughly 236GB of weights); quantized variants reduce this substantially.

vLLM

vllm serve \
    --model poolside/Laguna-S-2.1 \
    --tensor-parallel-size 4 \
    --tool-call-parser poolside_v1 \
    --reasoning-parser poolside_v1 \
    --enable-auto-tool-choice \
    --served-model-name laguna \
    --default-chat-template-kwargs '{"enable_thinking": true}'

Optional: speculative decoding with DFlash. Pair with the Laguna S 2.1 DFlash draft model by adding --speculative-config '{"model":"poolside/Laguna-S-2.1-DFlash","num_speculative_tokens":7,"method":"dflash"}'.

SGLang

python -m sglang.launch_server \
  --model-path poolside/Laguna-S-2.1 \
  --tp-size 4 \
  --reasoning-parser poolside_v1 \
  --tool-call-parser poolside_v1 \
  --trust-remote-code

TRT-LLM

trtllm-serve poolside/Laguna-S-2.1 --trust-remote-code \
    --tool_parser poolside_v1 --reasoning_parser laguna

Note the flag names differ from vLLM's (--tool_parser, and the reasoning parser is laguna, not poolside_v1).

llama.cpp

GGUF conversions are available at poolside/Laguna-S-2.1-GGUF. Serve with poolside's llama.cpp fork, branch laguna, which carries full Laguna support including DFlash speculative decoding. (Base Laguna support is also in upstream review: ggml-org/llama.cpp#25165.)

git clone --branch laguna https://github.com/poolsideai/llama.cpp
cd llama.cpp && cmake -B build && cmake --build build -j

./build/bin/llama-server -m laguna-s-2.1-Q4_K_M.gguf --jinja --port 8000

# with DFlash speculative decoding:
./build/bin/llama-server -m laguna-s-2.1-Q4_K_M.gguf \
  -md laguna-s-2.1-DFlash-BF16.gguf \
  --spec-type draft-dflash --spec-draft-n-max 7 -fa on --jinja --port 8000

Ollama

Run directly from the Ollama library:

ollama run laguna-s-2.1

Quantization variants are available as tags (q4_K_M, q8_0, f16, mxfp8, nvfp4, mlx-bf16), for example ollama run laguna-s-2.1:q8_0. The Laguna chat template is baked into the model, so tool-calling and interleaved reasoning work automatically.

Controlling reasoning

Laguna S 2.1 has native reasoning support and works best with preserved thinking: keep reasoning_content from prior assistant messages in the message history. The model will generally reason before calling tools and between tool calls, and may stop reasoning in follow-up steps if prior thinking blocks are dropped.

Thinking is controlled per request via the chat template:

extra_body={"chat_template_kwargs": {"enable_thinking": False}}

or at the server level with --default-chat-template-kwargs '{"enable_thinking": true}'. For agentic coding use cases we recommend enabling thinking and preserving reasoning in the message history.

License

This model is licensed under the OpenMDW-1.1 License.

Intended and Responsible Use

Laguna S 2.1 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 S 2.1 is subject to the OpenMDW-1.1 License, and should be used consistently with Poolside's Acceptable Use Policy. We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.

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

Downloads last month: 1,173

GGUF

Model size

118B params

Architecture

laguna

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for llmfan46/Laguna-S-2.1-Uncensored-Heretic-Vision-GGUF

Base model

poolside/Laguna-S-2.1

Finetuned

llmfan46/Laguna-S-2.1-Uncensored-Heretic

Quantized

(1)

this model