Meta's 8B instruction-tuned Llama 3.1. This is the size most people land on: capable enough for real work across chat, writing, summarisation, and everyday coding, while still running on a mainstream laptop or desktop.

It supports tool use and eight official languages, and it is the model Solus recommends by default for machines with a modern GPU or a reasonably fast CPU.

Single file: Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf

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.

Built with Llama.

Llama 3.1 is licensed under the Llama 3.1 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved. Your use of this model is governed by that license and by the Llama 3.1 Acceptable Use Policy.