An EigenLabs mirror of Recursive’s official MLX INT4 release of Flint, a mixture-of-experts language model for coding agents with 39.8B total and about 2.5B active parameters per token. The weights, tokenizer, chat template and configuration are byte-identical to RecursiveSI/flint-int4 at revision 3b93f9053b530488405ae9fca51d4900d6ce21f0. Only this model card is EigenLabs-authored; the upstream card is preserved unchanged as ORIGINAL_README.md. “INT4” describes the projections and experts; embeddings, scales, offsets and sensitive tensors use other precisions, so not every stored byte is four bits. Disk size is not a minimum-RAM specification: KV cache, context length, batching and runtime buffers add to it. Flint decides when to reason and emits its reasoning in blocks. This release has no trained forced-thinking switch, effort levels or thinking-budget control, so runtimes should reject those controls rather than emulate them. Tool calls use the template’s framed format (name……). For required or named tool choices, keep the caller’s messages and enforce the call in the sampler: an injected «call this tool now» instruction can push the model into writing calls inside unfinished…
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: EigenLabs
Теги: mlx, flint, moe, int4, reasoning, tool-use, apple-silicon, darkbloom
Лайков: 3 | Загрузок: 820
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.