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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use JackBinary/Laguna-S-2.1-GGUF-ROCMFPX 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 JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX
# Run inference directly in the terminal:
llama cli -hf JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX
# Run inference directly in the terminal:
llama cli -hf JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX

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 JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX
# Run inference directly in the terminal:
./llama-cli -hf JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX

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 JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX
# Run inference directly in the terminal:
./build/bin/llama-cli -hf JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX

Use Docker

docker model run hf.co/JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX

LM Studio
Jan

Ollama

How to use JackBinary/Laguna-S-2.1-GGUF-ROCMFPX with Ollama:

ollama run hf.co/JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX

Unsloth Studio

How to use JackBinary/Laguna-S-2.1-GGUF-ROCMFPX 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 JackBinary/Laguna-S-2.1-GGUF-ROCMFPX 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 JackBinary/Laguna-S-2.1-GGUF-ROCMFPX to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use JackBinary/Laguna-S-2.1-GGUF-ROCMFPX with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX

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": "JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use JackBinary/Laguna-S-2.1-GGUF-ROCMFPX with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX

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 "JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX" \
  --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 JackBinary/Laguna-S-2.1-GGUF-ROCMFPX with Docker Model Runner:
```
docker model run hf.co/JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX
```

Lemonade

How to use JackBinary/Laguna-S-2.1-GGUF-ROCMFPX with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX

Run and chat with the model

lemonade run user.Laguna-S-2.1-GGUF-ROCMFPX-Q8_0_ROCMFPX

List all available models

lemonade list

Hermes Agent

How to use JackBinary/Laguna-S-2.1-GGUF-ROCMFPX with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX

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 JackBinary/Laguna-S-2.1-GGUF-ROCMFPX:Q8_0_ROCMFPX

Run Hermes

hermes

Atomic Chat

Laguna-S-2.1 — ROCmFPX hybrid quant (Q4 experts + Q8 rest)

This is a quantization of unsloth/Laguna-S-2.1-GGUF (BF16) (the original model is Poolside's Laguna S 2.1, a 118B-total / 8B-activated MoE with 256 routed experts).

You need the ROCmFPX fork of llama.cpp (or a llama.cpp build with ROCmFPX support). This file uses the experimental q4_0_rocmfp4_fast (type 101) and q8_0_rocmfpx (type 103) weight formats, which stock llama.cpp releases do not understand — loading it elsewhere will fail with an unknown tensor type error.

Recipe

Tensor group	Type	Count
Routed experts: `blk.N.ffn_{gate,up,down}_exps`	`q4_0_rocmfp4_fast` (4.25 bpw)	141
Everything else quantizable (attention, shared experts, embeddings, output head)	`q8_0_rocmfpx` (8.25 bpw)	386
Norms, biases, router weights/scales	`f32` (untouched)	287

Total size: ~61.6 GB (4.39 bpw) vs 224 GB BF16 source — single merged file, no shards
Rationale: routed experts dominate parameters (~97%) and tolerate 4-bit well; everything else stays near-lossless at 8-bit.

How it was made

# from the ROCmFPX fork (CPU-only build works fine for quantization)
llama-quantize \
  --tensor-type "ffn_(gate|up|down)_exps=q4_0_rocmfp4_fast" \
  Laguna-S-2.1-BF16-00001-of-00005.gguf \
  Laguna-S-2.1-Q8_0_ROCMFPX-Q4FAST-experts.gguf Q8_0_ROCMFPX
# then merged from 5 shards: llama-gguf-split --merge ...

Note the leading dense layer (blk.0) keeps its dense FFN at q8_0_rocmfpx — only the routed expert tensors were overridden.

Usage

# build ROCmFPX for your GPU (see the repo README; e.g. Strix Halo):
env JOBS=16 scripts/build-strix-rocmfp4-mtp.sh

# run (Vulkan was fastest in upstream tests on Strix Halo):
./build-strix-rocmfp4/bin/llama-cli \
  -m Laguna-S-2.1-Q8_0_ROCMFPX-Q4FAST-experts.gguf \
  -dev Vulkan0 -ngl 999 -fa on --jinja

Benchmarks

Benchmarks are pending — placeholder table below.

Backend / GPU	Prompt (tok/s)	Generation (tok/s)	Context	Notes
TBD	TBD	TBD	TBD	TBD

Quality comparison vs BF16 source (perplexity / KLD): TBD.

Attribution & license

Quantized from: unsloth/Laguna-S-2.1-GGUF (BF16 shards)
Original model: Poolside Laguna S 2.1
License: openmdw-1.1 (inherited from the source model)
Quant formats by the ROCmFPX project

Downloads last month: 47

GGUF

Model size

118B params

Architecture

laguna

Hardware compatibility

8-bit

Inference Providers NEW

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

Model tree for JackBinary/Laguna-S-2.1-GGUF-ROCMFPX

Base model

poolside/Laguna-S-2.1

Quantized

unsloth/Laguna-S-2.1-GGUF

Quantized

(2)

this model

Collection including JackBinary/Laguna-S-2.1-GGUF-ROCMFPX

ROCmFPX GGUF Quants

Collection

Hybrid q4/q8 ROCmFPX GGUF quants. Requires the ROCmFPX fork of llama.cpp. • 4 items • Updated about 17 hours ago