Model size: 309B parameters (15B active). The «52B params» figure in the Hugging Face sidebar is not a parameter count: the site counts the packed 16-bit words of the EXL3 format. Hardware: sized to fit one 128 GB machine. The pack is in the standard EXL3 format, so it is not tied to one GPU; it has been tested only on AMD Strix Halo (Ryzen AI Max+ 395) with the Kyojin engine, and other hardware is untested. An EXL3 quantisation of XiaomiMiMo/MiMo-V2.6-Flash-MOPD (MoE, 309B total, 15B active, per the upstream card) for one 128 GB unified-memory machine (AMD Ryzen AI Max+ 395, gfx1151). The three MTP heads are kept at 4 bits or more in the pack; the engine does not use them; speculative decoding runs on the separate 4 bpw drafter in drafter/ (see Speed). This pack holds the text model only (no vision or audio encoders). It runs on the Kyojin engine, built on ExLlamaV3. Quantised by Yamz. Not affiliated with Xiaomi. — Quality. Against the official FP8 model on 125 held-out rows: KLD 0.0713, top-1 agreement 91.99 %. The tuning overlay (see below) lowers KLD by 1.86 % on the same rows compared with the pack without it. — Size. 105.04 GB for a 309B-total MoE: one 128 GB machine holds…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: yamz-labs
Теги: exllamav3, mimo_v2, exl3, quantized, mimo, moe, rocm, strix-halo
Лайков: 3 | Загрузок: 419
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
