Select from evidence on your workload, not a generic leaderboard. Start with the smallest checkpoint that meets your quality target, then verify its terms, training support, and deployment path before investing in a full run.
Build representative success, failure, boundary, safety, and out-of-distribution cases. Keep them out of training and prompt iteration.
Test the same rubric with prompting, few-shot examples, retrieval, and candidate base models. Fine-tuning should solve a measured gap.
Run a short adapter experiment, record the full configuration, and promote only if the gain survives held-out and safety evaluation.
Snapshot reviewed August 2026. This is a starting set, not a ranking or a promise that every checkpoint supports every tuning method. Follow the official source for current files and terms.
A Google-supported open-weight family with documented local and cloud tuning paths.
Check: Choose the exact checkpoint and format only after checking the current Gemma terms, framework guide, and memory requirements.
Open the official model sourceA broad open-weight family worth evaluating for multilingual, coding, and multimodal workloads.
Check: The collection contains models with very different architectures and sizes; verify each model card and chat template.
Open the official model sourceOpen-weight models with official deployment and, for selected checkpoints, fine-tuning guidance.
Check: Some recent checkpoints are mixture-of-experts models whose total weight footprint is much larger than their active parameter count.
Open the official model sourceOpenAI open-weight reasoning models with an official model card and fine-tuning notes.
Check: Preserve the required Harmony response format and benchmark memory on the exact training stack before selecting a checkpoint.
Open the official model sourceNVIDIA’s open-weight family aimed at agent and tool-use workloads, in tiers from compact to very large mixture-of-experts checkpoints, with data and recipes published for parts of the family.
Check: Tiers differ in license and architecture; verify the full weight footprint of a mixture-of-experts checkpoint and your framework’s support for it before piloting.
Open the official model sourceSmall encoder models for extraction, classification, and PII detection that train quickly and serve cheaply; tuned task models of this class can match far larger generalists on narrow tasks.
Check: These are schema-driven task models, not chat models; confirm the task fits the interface and beat a generalist baseline on your own labels before committing.
Open the official model sourceParameter count alone does not predict training memory. Precision, sequence length, attention implementation, optimizer, batch size, adapters, and sharding all matter. The costliest boundary is the single accelerator: once a pilot no longer fits one device even with adapters and quantization, training becomes a distributed-systems project.
“Open weight” is not a license category: some releases publish weights, data, and training code under permissive terms, while others ship weights alone with revenue or field-of-use conditions. Review the checkpoint’s terms and notices; do not infer rights from the model family name.
A tuned model can regress outside the target task. Test base capabilities, abuse cases, privacy leakage, and refusal behavior before each release.
Never purchase hardware from a generic VRAM estimate. Reproduce a representative pilot with the exact checkpoint, precision, sequence length, and framework, or obtain a current provider quote that includes training, storage, serving, and data-transfer costs.