Instructions to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit"
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 SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit"
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 "SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Laguna-XS-2.1-sbQ-4bit
A 4-bit imatrix MLX quantization of poolside/Laguna-XS-2.1, calibrated on a generic code + multilingual corpus.
This repo exists as the control. It is the exact same build — same bits, same tool, same commit — as Laguna-XS-2.1-sbQ-cal-4bit, except the imatrix calibration corpus: generic text here, real agent traces there. The comparison between the two is the finding — calibration shifts behaviour and speed at equal perplexity — and a comparison you cannot reproduce is a story, so both sides are published. Read the sbQ-cal card for the full grid and the probe battery; this card carries this build's own numbers.
Published by SoftBacon Software. We publish the whole ladder, losing rungs included. On behavioural probes this build ties or loses to its agent-calibrated sibling on every probe (by 1–2 passes of 96, zero inversions) — that is precisely why it is here.
Measurements (same regime as the sbQ-cal card, 2026-08-23/24)
| this build | sbQ-cal-4bit | |
|---|---|---|
| size | 18 GB | 18 GB |
| decode tok/s | 136.5 | 131.5 |
| speculative tok/s | 320.6 | 315.8 |
| held-out NLL (merged split, cap 8192) | 1.4806 | 1.4802 |
| needle n=72 | 71/72 | 71/72 |
| verify_before_assert (n=96) | 0.833 | 0.844 |
| say_not_measured (n=96) | 0.354 | 0.375 |
It is the slightly faster of the pair — calibration shapes bit
allocation, and bit allocation shapes the compute layout — so if you want
raw decode speed over agentic-behaviour margins, this is the rung to take.
The single dropped needle cell (ctx32000_pos0.5) is dropped by the 8-bit
reference too: workload artifact, not quant damage.
Full expert-activation report from calibration: oq_imatrix_report.json
(0 dark experts of 256 for this corpus).
What's in the repo
MLX safetensors + tokenizer + chat template, PROVENANCE.md,
oq_build.json, oq_imatrix_report.json, and LICENSE.md (OpenMDW-1.1,
inherited from the base model).
Reproduce
Build tool and measurement harness: github.com/SoftBacon-Software.
Built from poolside's official BF16 with no third party in the chain. The
sbQ family name marks SoftBacon builds — unrelated to poolside releases
and to community oQ-series quants.
- Downloads last month
- -
4-bit
Model tree for SoftBacon-Software/Laguna-XS-2.1-sbQ-4bit
Base model
poolside/Laguna-XS-2.1