---
base_model: poolside/Laguna-S-2.1
library_name: gguf
pipeline_tag: text-generation
tags:
- gguf
- quantized
- laguna
- mixture-of-experts
- q2_k
- q3_k
- ds4
---

# Laguna S 2.1 GGUF

This repository contains a reduced-memory Laguna S 2.1 quantization for
DwarfStar.

## Mixed Q2_K/Q3_K variant

`laguna-s-2.1-RoutedQ2_K-Last27Q3_K.gguf` keeps every non-routed tensor
byte-identical to Poolside's `laguna-s-2.1-Q4_K_M.gguf` at revision
`706fa69799926b6afde1af9e24ca2a4923f110a1`. Only routed expert tensors were
requantized using the source importance matrix:

- routed layers 1 through 20: Q2_K gate, up, and down
- routed layers 21 through 47: Q3_K gate, up, and down
- all other tensors: unchanged from the official Q4_K_M GGUF

The file is 48,260,803,968 bytes (44.946 GiB), intended for full-residency
inference on 64 GiB systems. Runtime memory also depends on context size and
KV-cache allocation.

SHA-256:

```text
61fc66596597985cb9408a8530de6322d9e0d5b1d2ad4ed6503938018e0ce903
```

## DwarfStar

Q3_K routed Laguna inference is supported starting with DwarfStar commit
`938227a2`.

```sh
./download_model.sh laguna-q2-q3
./ds4 -m gguf/laguna-s-2.1-RoutedQ2_K-Last27Q3_K.gguf -p "Hello"
```

On an Apple M5 Max, the tested model reached approximately 514 tokens/second
for a 4096-token prefill and 63 tokens/second steady-state generation.

Against 100 official continuation vectors, the mixed model obtained average
NLL 0.2583, 87/100 first-token matches, and average matching-prefix length
9.50 tokens. The corresponding full Q4_K_M measurements were 0.2352, 92/100,
and 10.86.