mlx-community·released 2025-02-151 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
Released in 2025 by mlx-community, this model carries 8.03 billion parameters, placing it in the mid-size range rather than at the compact or frontier extremes. That mid-size scale is a deliberate balance: far more headroom than a small model offers, while staying cheaper and easier to run than large-scale alternatives.
4 cited facts
This model is not yet benchmarked, as it is scored on no tracked benchmarks. It holds no current top score on any benchmark.
2 cited facts
Because avg sota gap is unknown, the position must be read from sota leader count instead: this model holds the top score on 0 benchmarks, which means it shows no category leadership yet. With no benchmark where it leads, the reading is simply that it sits behind the pack rather than at the frontier, and no average points-behind figure can be stated.
3 cited facts
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: huggingface_models
Llama-3.1-8B-Instruct-4bit is an AI model developed by mlx-community, released 2025-02-15. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.