---
title: Laguna-S-2.1-OptiQ-2bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Laguna-S-2.1-OptiQ-2bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Laguna-S-2.1-OptiQ-2bit.md"
repository: mlx-community/Laguna-S-2.1-OptiQ-2bit
last_updated: 2026-09-15
license: openmdw-1.1
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - laguna
architectures:
  - LagunaForCausalLM
base_model:
  - poolside/Laguna-S-2.1
base_model_relation: quantized
parameters: 12.9B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 42
stars: 0
tags:
  - laguna
  - laguna-s-2.1
  - mlx
  - quantized
  - 2bit
  - mixed-precision
  - optiq
  - static
  - moe
  - ssd-streaming
  - apple-silicon
  - text-generation
---

# Laguna-S-2.1-OptiQ-2bit

> Laguna-S-2.1-OptiQ-2bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Laguna-S-2.1-OptiQ-2bit

mlx-community/Laguna-S-2.1-OptiQ-2bit 是 ModelScope 魔搭社区上的 12.9B 参数text-generation模型，采用 openmdw-1.1 许可，基于 poolside/Laguna-S-2.1 构建。

- **Repository**: mlx-community/Laguna-S-2.1-OptiQ-2bit
- **License**: openmdw-1.1
- **Tasks**: text-generation
- **Parameters**: 12.9B
- **Base model**: poolside/Laguna-S-2.1
- **Tags**: laguna, laguna-s-2.1, mlx, quantized, 2bit, mixed-precision, optiq, static, moe, ssd-streaming, apple-silicon, text-generation
- **Downloads**: 42
- **Stars**: 0
- **Last updated**: 2026-09-15

Source: https://www.modelscope.cn/models/mlx-community/Laguna-S-2.1-OptiQ-2bit

---

# mlx-community/Laguna-S-2.1-OptiQ-2bit

> **Built with [mlx-optiq](https://mlx-optiq.com)**, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. [All OptiQ quants](https://mlx-optiq.com/models) · [Docs](https://mlx-optiq.com/docs/) · [Laguna family](https://mlx-optiq.com/docs/laguna)

**A 117-billion-parameter coding model that runs in 9.4 GB of RAM on a Mac.** This is a 2-bit mixed-precision MLX quant of poolside's Laguna-S-2.1 (235 GB at bf16), produced by [mlx-optiq](https://mlx-optiq.com/). It is 41 GB on disk. While it generates, only ~9.4 GB sits in RAM: attention, the router, the shared expert and the layer edges stay resident, and the routed mixture-of-experts weights stream off the SSD as the router selects them.

Laguna-S is a sparse mixture-of-experts reasoning model built for coding and agents: 48 layers, 256 experts with 10 active per token. Asked to write Flappy Bird as a single HTML file, the 2-bit model produced a complete, working game with gravity, pipe collisions, scoring and restart, all in one pass. Here it is, playing the game it wrote:

![Laguna-S-2.1 2-bit playing the Flappy Bird it wrote](flappy.gif)

The full game it generated is in this repo as [`flappy_bird.html`](flappy_bird.html). Open it in any browser.

## What it is

| Property | Value |
|---|---|
| Base | poolside/Laguna-S-2.1 (sparse MoE, 256 experts, 10 active per token, 48 layers) |
| Method | OptiQ `static`, structural per-layer bit allocation, no calibration |
| Bit-widths | 4-bit on attention, router, shared expert and layer edges; 2-bit on the routed experts |
| Achieved bits-per-weight | 3.01 |
| On disk | 41 GB |
| Resident while running | ~9.4 GB (routed experts streamed) |
| Decode speed | ~3 tok/s on an M3 Max, SSD-bound |

No Capability Score is published for this quant. At 2-bit on the routed experts the point of the artifact is that a 117 B MoE runs at all on consumer Apple Silicon and stays coherent enough to write working code. For benchmarked quality in the Laguna family, use [Laguna-XS-2.1-OptiQ-4bit](https://huggingface.co/mlx-community/Laguna-XS-2.1-OptiQ-4bit) (Capability Score 85.81).

For a model this large, exact calibration-driven sensitivity is impractical (it would run for days and needs the full model resident as a reference), so OptiQ's `static` method assigns bits from architecture alone. See the [methods comparison](https://mlx-optiq.com/docs/sensitivity).

## Run it

Laguna ships under an architecture stock mlx-lm does not know, so `import optiq` once to register it:

```bash
pip install "mlx-optiq>=0.4.7"
```

The routed experts are too large to sit resident, so serve it with SSD expert streaming. `optiq serve` turns this on automatically for a MoE quant that would not fit in RAM (`--stream-experts` forces it):

```bash
optiq serve --model mlx-community/Laguna-S-2.1-OptiQ-2bit
```

That gives you an OpenAI + Anthropic-compatible endpoint with mixed-precision KV cache, tool-call healing and prompt caching. Only the routed experts stream per token; attention, the router and the shared expert stay resident, so the footprint stays ~9.4 GB no matter how large the model on disk is. Laguna is a reasoning model, it thinks before answering, so give it a generous token budget.

## Notes

This is an **extreme quant**. 2-bit on the routed experts is lossy, and reference-quality generation should use the bf16 weights or a higher-bit quant. What it demonstrates is coherence at a footprint that fits a 16 GB Mac, and a working game written in a single pass.

## Links

- **Project website:** [mlx-optiq.com](https://mlx-optiq.com/)
- **All OptiQ quants:** [mlx-optiq.com/models](https://mlx-optiq.com/models)
- **PyPI:** [pypi.org/project/mlx-optiq](https://pypi.org/project/mlx-optiq/)
- **Base model:** [poolside/Laguna-S-2.1](https://huggingface.co/poolside/Laguna-S-2.1)