Instructions to use kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF",
	filename="Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-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 kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP

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 kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./llama-cli -hf kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP

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 kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP

Use Docker

docker model run hf.co/kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP

LM Studio
Jan
Ollama
How to use kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF with Ollama:
```
ollama run hf.co/kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP
```

Unsloth Studio

How to use kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-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 kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-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 kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF to start chatting

How to use kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP

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": "kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-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 kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP

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 kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP

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 "kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP" \
  --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"

Docker Model Runner
How to use kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF with Docker Model Runner:
```
docker model run hf.co/kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP
```

Lemonade

How to use kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF:Q4_0_ROCMFP

Run and chat with the model

lemonade run user.Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF-Q4_0_ROCMFP

List all available models

lemonade list

Laguna-S-2.1 Q4_0_ROCMFP4_STRIX_LEAN (GGUF)

First public-ready Laguna-S-2.1 ROCmFP4 "Strix Lean" quant for AMD Ryzen AI Max+ 395 (gfx1151 / Radeon 8060S).

⚠️ Not compatible with upstream llama.cpp. Requires the charlie12345/ROCmFPX fork built with HIP + ROCmFP4 kernels.

Files

File	Size	Notes
`Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN.gguf`	~58.34 GiB	4.26 BPW (quantize report)
`SHA256SUMS`

Base model: poolside/Laguna-S-2.1
F16 source: poolside/Laguna-S-2.1-GGUF laguna-s-2.1-F16.gguf (235202258240 bytes)

Hardware / stack (validated)

Box: amdaimax2 — Ryzen AI Max+ 395, gfx1151, 128 GB unified
ROCm 7.2.4 (/opt/rocm-7.2.4, clang 22)
Fork: charlie12345/ROCmFPX @ 3edc3d31ee5ebcea47fd7e0f42c89767bb4245db

Build recipe (HIP-only)

export PATH=/opt/rocm-7.2.4/bin:$PATH
export HIP_PATH=$(hipconfig -R)
export HIPCXX=$(hipconfig -l)/clang
cmake -B build \
  -DGGML_HIP=ON -DGPU_TARGETS=gfx1151 \
  -DGGML_HIP_ROCWMMA_FATTN=ON -DGGML_HIP_NO_VMM=ON -DGGML_HIP_MMQ_MFMA=ON \
  -DCMAKE_BUILD_TYPE=Release -DGGML_VULKAN=OFF -DLLAMA_BUILD_WEBUI=OFF
cmake --build build -j 4   # prefer -j 4..8 on 128GB Strix; avoid -j32

Quantize

build/bin/llama-quantize \
  laguna-s-2.1-F16.gguf \
  Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN.gguf \
  Q4_0_ROCMFP4_STRIX_LEAN 8
# quant size = 59739.82 MiB (4.26 BPW)

Runtime (required)

export LD_LIBRARY_PATH=<build/bin>:/opt/rocm/lib
export HSA_OVERRIDE_GFX_VERSION=11.5.1
export GGML_HIP_ENABLE_UNIFIED_MEMORY=1

llama-server --host 127.0.0.1 --port 8099 \
  --n-gpu-layers 999 --flash-attn on -dio --no-warmup --jinja \
  --model Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN.gguf \
  --ctx-size 65536 --cache-type-k q8_0 --cache-type-v q8_0 --parallel 1 \
  --temp 0.2 --top-p 0.95 --top-k 20 --min-p 0.05 --repeat-penalty 1.1 --repeat-last-n 256 \
  --chat-template-kwargs '{"enable_thinking":true}' --reasoning-budget 512

-dio is required for reliable cold load of large Laguna GGUFs on this stack (mmap path can hang).

A/B vs Q4_K_M (same binary, same flags, cold load)

Quant	prompt_n	prompt tok/s	decode tok/s (256-cap gen)	GGUF size
Q4_K_M	8116 (~8K)	445.6	17.36	71 GiB
ROCmFP4 STRIX_LEAN	8116 (~8K)	381.8	28.23	58.3 GiB
Q4_K_M	32223 (~32K)	372.4	14.15	71 GiB
ROCmFP4 STRIX_LEAN	32223 (~32K)	327.3	20.32	58.3 GiB

Decode speedup: +62.6% @ ~8K, +43.6% @ ~32K
Size: −18% (58.3 vs 71 GiB)
Prompt processing slightly slower on ROCmFP4 (−14% / −12%)

Quality / tools / reasoning

Shared prompts (reasoning, code, tool-call plan, short math with thinking):

Check	Q4_K_M	ROCmFP4	Verdict
Bat/ball $0.05	correct	correct	parity
is_palindrome plan	coherent thinking	coherent thinking	parity
get_weather Paris/Tokyo tool JSON	clean calls	clean calls	parity
enable_thinking / reasoning-budget	works	works	parity

Did we lose anything? No quality regression observed on the four shared prompts. We gain decode speed and lose model file size; prefill is slightly slower.

License

Follow the base model (poolside/Laguna-S-2.1) license terms.

Downloads last month: 180

GGUF

Model size

118B params

Architecture

laguna

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for kingjones777/Laguna-S-2.1-Q4_0_ROCMFP4_STRIX_LEAN-GGUF

Base model

poolside/Laguna-S-2.1

Quantized

(70)

this model