GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

dev7a/Laguna-S-2.1-DFlash-GGUF overview

Laguna S 2.1 DFlash GGUF This repository contains a Q8 0 GGUF conversion of Poolside's DFlash drafter for Laguna S 2.1. It is an auxiliary draft model. It is n…

gguflagunadflashspeculative-decodingdraft-modelbase_model:poolside/Laguna-S-2.1-DFlashbase_model:quantized:poolside/Laguna-S-2.1-DFlashlicense:otherendpoints_compatibleregion:usconversational

Runs locally from ~1.11 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
Author

Repository Files & Downloads

1 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Laguna-S-2.1-DFlash-Q8_0.ggufGGUFQ8_01.11 GBDownload

Model Details

Model IDdev7a/Laguna-S-2.1-DFlash-GGUF
Authordev7a
Pipeline
Licenseother
Base modelpoolside/Laguna-S-2.1-DFlash
Last modified2026-08-11T10:21:19.000Z

Model README

---

license: other

license_name: openmdw-1.1

library_name: gguf

base_model: poolside/Laguna-S-2.1-DFlash

base_model_relation: quantized

tags:

- gguf

- laguna

- dflash

- speculative-decoding

- draft-model

---

Laguna S 2.1 DFlash GGUF

This repository contains a Q8_0 GGUF conversion of Poolside's DFlash drafter

for Laguna S 2.1. It is an auxiliary draft model. It is not a standalone

language model and does not include the Laguna S 2.1 target weights.

Artifact

| File | Bytes | SHA-256 |

| --- | ---: | --- |

| Laguna-S-2.1-DFlash-Q8_0.gguf | 1,188,535,328 | 94d5d6d93acb2dfb1209599bc099ebc5b30e959a3a1200dcaebfb01e3f480e43 |

The GGUF has six DFlash layers and target taps [2, 11, 20, 30, 39, 48].

Its 49 matrix tensors use Q8_0. Its 27 normalization and bias tensors remain

F32.

Download

hf download dev7a/Laguna-S-2.1-DFlash-GGUF Laguna-S-2.1-DFlash-Q8_0.gguf

Use this drafter only with a compatible Laguna S 2.1 target and a runtime that

supports the standardized llama.cpp dflash GGUF schema. In NS4, use catalog

coordinate dev7a/laguna-s:dflash.

Provenance and reproduction

The source weights are Poolside's SafeTensors at revision

b0486d1586daa0d56435c508108171fc1c8daff9. The target tokenizer comes from

Laguna S 2.1 revision 00af5a51782109b587a3b3bbf11875e566036fa7.

Conversion uses Poolside's llama.cpp revision

06f8cebd7fe728687be3d19f8bdedb70d75883af.

The source manifest records every downloaded file, byte size, and SHA-256.

The dependency locks contain hashes and use binary packages only. The released

file and a clean repeated conversion were byte-identical.

Reproduce on Linux AArch64 with Python 3.12:

python3.12 scripts/download_sources.py --destination sources
python3.12 scripts/reproduce.py --sources sources --repeat-check

Verify the release without third-party Python packages:

python3.12 scripts/verify.py Laguna-S-2.1-DFlash-Q8_0.gguf

This is a community conversion, not an official Poolside release. The weights

remain under OpenMDW-1.1. The unmodified upstream license is in LICENSE.

The conversion-code license and third-party notices are in LICENSE.code and

THIRD_PARTY_NOTICES.md.

Run dev7a/Laguna-S-2.1-DFlash-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models