Modelpublic

Fazmin/solus_v1_llama-3.2-3b-instruct-q4

sourceHugging Facellama3.2updated 2mo agoView on Hugging Face

0likes7downloads

Model Card

Llama 3.2 3B Instruct — Solus v1

The larger of Meta's two small Llama 3.2 instruction-tuned models. At roughly 3.2B parameters it is a genuine general-purpose assistant that still fits comfortably on a laptop, and it is a noticeable step up from the 1B on instruction following, summarisation, and multi-turn chat.

Officially supports eight languages. A good default when you want everyday chat and writing quality without a discrete GPU.

Specifications


Parameters	3B
Quantization	Q4KM
File size	1.88 GB
Minimum RAM	5.00 GB
Minimum VRAM	not required
Context length	16,384 tokens
SHA-256	`6c1a2b41161032677be168d354123594c0e6e67d2b9227c84f296ad037c728ff`

Single file: Llama-3.2-3B-Instruct-Q4_K_M.gguf

Quantization

Quantization performed at the Faculty of Engineering, McMaster University.

The GGUF conversion this build is derived from was produced by bartowski, and the weights here are a byte-for-byte copy of that file — the SHA-256 above matches the upstream artifact.

Provenance

—Original model: meta-llama/Llama-3.2-3B-Instruct
—Upstream GGUF: bartowski/Llama-3.2-3B-Instruct-GGUF
—Mirrored for Solus, a desktop app for running language models entirely on your own machine.

Usage

bash

llama-cli -m Llama-3.2-3B-Instruct-Q4_K_M.gguf -cnv

License

Built with Llama.

Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved. Your use of this model is governed by that license and by the Llama 3.2 Acceptable Use Policy.