---
license: apache-2.0
base_model: poolside/Laguna-M.1
base_model_relation: quantized
library_name: mlx
pipeline_tag: text-generation
tags:
  - mlx
  - apple-silicon
  - laguna
  - laguna-m.1
  - moe
  - quantized
  - conversational
---

# Laguna-M.1-MLX-Q3

A community **MLX** (Apple Silicon) build of Poolside's
[**Laguna M.1**](https://huggingface.co/poolside/Laguna-M.1) — a 225B-total /
23B-active Mixture-of-Experts model — quantized to **3-bit** so it runs locally on
a 128 GB Mac.

Poolside ships official support for vLLM, SGLang, Transformers and TRT-LLM (all CUDA
/ datacenter). This is the **Apple Silicon / edge** path.

> **Expected quality.** Uniform 3-bit on a 23B-active MoE is the size/quality
> floor. Degradation shows up first on long-context and agentic prompts. If you
> have the RAM headroom, prefer a higher-bit or mixed-precision build.

> Not affiliated with Poolside. Weights © Poolside, Inc., released under Apache 2.0.
> Converted from the public release `poolside/Laguna-M.1-FP8` (weights verified
> byte-identical to the public checkpoint; tokenizer, chat template and generation
> config taken from the public release).

## Use

`laguna` isn't upstream in mlx-lm yet
([PR #1415](https://github.com/ml-explore/mlx-lm/pull/1415) pending). Until it
lands, install mlx-lm from the branch that ships the model file **and the
tool-call parser fix** (needed for tool use in agentic clients), pinned to a commit:

```bash
pip install "git+https://github.com/eauchs/mlx-lm.git@5b0c0667f4a8c25ee9bb9ef729ab64822d1b246e"

mlx_lm.generate --model ox-ox/Laguna-M.1-MLX-Q3 \
  --prompt "Write a Python retry wrapper with exponential backoff." \
  --temp 1.0 --top-k 20
```

`--temp 1.0 --top-k 20` is Poolside's recommendation for the full-precision
model. At 3-bit it's on the aggressive side; if output looks unstable, try
`--temp 0.6 --top-p 0.95`.

Once the PR is merged, this is just `pip install -U mlx-lm` + the `mlx_lm.generate`
line — no extra step.

## Performance

| Quant | Hardware | Throughput | Peak RAM |
|-------|----------|-----------|----------|
| Q3 | Apple M3 Max 128 GB | ~26.5 tok/s | ~100 GB |

## Architecture

70 layers (3 dense SwiGLU + 67 sparse MoE), 256 experts + 1 shared, top-k=16 sigmoid
routing; global attention 64 Q / 8 KV heads, head_dim 128, QK-norm + softplus output
gating; RoPE with YaRN. See the [official model card](https://huggingface.co/poolside/Laguna-M.1)
for full details and benchmarks.

## License

Apache 2.0 (weights and conversion). © Poolside, Inc. for Laguna M.1.

## Citation

Conversion by Théophile Lafargue ([@eauchs](https://x.com/eauchs)). Model by
Poolside — see their [technical report](https://huggingface.co/poolside/Laguna-M.1).