Modelpublic

Fazmin/solus_v1_llama-3.2-1b-instruct-q4

sourceHugging Facellama3.2updated 2mo agoView on Hugging Face

0likes25downloads

Model Card

Llama 3.2 1B Instruct — Solus v1

Meta's smallest instruction-tuned Llama 3.2 model. At roughly 1.2B parameters it is built for on-device use, and it will run on hardware that cannot host anything larger. It handles short conversational turns, light rewriting, and simple summarisation well, and it officially supports eight languages.

Expect it to trade depth for speed: it is not the model to reach for on multi-step reasoning or long documents, but it responds almost instantly and has a very small memory footprint.

Specifications


Parameters	1B
Quantization	Q4KM
File size	770.28 MB
Minimum RAM	3.00 GB
Minimum VRAM	not required
Context length	8,192 tokens
SHA-256	`6f85a640a97cf2bf5b8e764087b1e83da0fdb51d7c9fab7d0fece9385611df83`

Single file: Llama-3.2-1B-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-3.2-1B-Instruct
—Upstream GGUF: bartowski/Llama-3.2-1B-Instruct-GGUF
—Mirrored for Solus, a desktop app for running language models entirely on your own machine.

Usage

bash

llama-cli -m Llama-3.2-1B-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.