Laguna-XS-2.1-3bit

mlx-community/Laguna-XS-2.1-3bit

Laguna-XS-2.1-3bit is a text generation model from mlx-community. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as openmdw-1.1.

Converted from poolside/Laguna-XS-2.1 to MLX format, quantized to 3 bits (group size 64, 3.503 bpw effective).

Downloads · 30 days

133

12% of all-time downloads

All-time downloads

1.1K

Public

Parameters

33.4B

14.6 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors14.6 GB · 100%

Parameter types

How the weights are stored.

U3233.4B · 100%

Try a prompt

Base models

poolside/Laguna-XS-2.1

Model card

From the Hugging Face model README

Laguna-XS-2.1 (MLX, 3bit)

Converted from poolside/Laguna-XS-2.1 to MLX format, quantized to 3 bits (group size 64, 3.503 bpw effective).

Notes

Works with mlx-vlm and oMLX (forcing the model's vlm mode). mlx-lm doesn't support the laguna architecture yet — there's an open PR: mlx-lm#1223.
Sometimes I got an empty </think> tag at the start of responses, which isn't that common. It won't affect anything tho.

Performance

Measured with oMLX's benchmark harness on a Macbook Pro M5 Max 128GB 40 GPU (single request, 128 generated tokens):

prompt	gen tok/s	prefill tok/s	TTFT ms	peak GB
1k	137.2	3959	259	14.3
4k	128.8	4003	1023	14.9
8k	124.4	3807	2152	15.0
16k	114.6	3214	5098	15.3
32k	98.8	2612	12546	15.9

Variants

Variant	bpw	Disk	gen tok/s (1k → 32k)
bf16	16	62 GB	70.6 → 58.7
8bit	8.500	33 GB	95.4 → 76.7
6bit	6.501	25 GB	102.9 → 80.9
5bit	5.502	21 GB	115.9 → 87.7
4bit	4.503	18 GB	126.0 → 91.3
3bit (this repo)	3.503	14 GB	137.2 → 98.8

Usage

uvx --from mlx-vlm mlx_vlm.generate --model mlx-community/Laguna-XS-2.1-3bit --prompt "..." --max-tokens 300

License

OpenMDW-1.1, inherited from the base model.

Task: Text Generation
Library: mlx
Type: laguna
License: openmdw-1.1
Created: Jul 3, 2026
Updated: Jul 3, 2026