prism-ml·released 2026-07-041 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
This model is a compact 1.72-billion-parameter release from prism-ml, arriving in 2026 at a scale that favors efficiency and low inference cost over raw capacity. That small footprint means the trade-off is deliberate: less headroom for demanding workloads, but far cheaper and leaner to run than a frontier-scale system.
4 cited facts
This model is not yet benchmarked, with no tracked benchmark scores to report. As a result, it holds no current top score on any tracked evaluation.
2 cited facts
The average SOTA gap is unknown, and the model holds the top score on 0 benchmarks, so it shows no genuine category leadership yet.
2 cited facts
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: huggingface_models
Bonsai-27B-mlx-1bit is an AI model developed by prism-ml, released 2026-07-04. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.