01 / 06
ENJP

MN-Core:
Ultimate
inference
chip

01 — Performance

MN-Core brings lightning-fast inference.

Text generation — side by side

MN-Core™ L1000

How will next-generation AI chips break the memory wall? Next-generation Al chips will move computation closer to data. By combining 3D-Stacked memory, chiplet-based accelerators, and intelligent dataflow scheduling, they can reduce the energy and delay spent moving tensors across a system. The result is an Al engine that keeps models continuously supplied with data, scales efficiently, and turns real-time reasoning into an everyday capability-from autonomous laboratories to personal scientific assistants.

Competitor

How will next-generation AI chips break the memory wall? Next-generation Al chips will move computation closer to data. By combining 3D-Stacked memory, chiplet-based accelerators, and intelligent dataflow scheduling, they can reduce the energy and delay spent moving tensors across a system. The result is an Al engine that keeps models continuously supplied with data, scales efficiently, and turns real-time reasoning into an everyday capability-from autonomous laboratories to personal scientific assistants.

0x

推論速度

同一システムサイズのまま、10倍の推論性能。

0GB

メモリ容量

128GBのメモリを備え、100BクラスのLLMの超文脈推論を1マシンで完結。

0+TB/s

バンド幅

ロジックとメモリを上下に積層し、LLM推論のボトルネックであるメモリ帯域を最大化。

Performance estimates are based on internal modeling and are subject to change. Actual performance may vary.

02 — Why MN-Core

3D-Stacked DRAM enables
massive memory bandwidth

ロジックとメモリを上下方向に積層し、平面全体で接続する。

Compute Efficiency

実績ある計算機アーキテクチャーが生む、優れた電力効率

Optimal Architecture
for 3D-Stacked DRAM

3D積層DRAMの特徴を最大限活用できる計算機アーキテクチャ

3D-Stacked DRAM構造の模式図

03 — Basic Specs

MN-Core L1000

Memory Size
128GB
Performance
10x
Memory Bandwidth
40+TB/s

in One Workstation in 2027

All specifications and performance figures are preliminary and subject to change without notice. Performance estimates are based on internal modeling and are subject to change. Actual performance may vary.

05 — Future Vision

最速、最高効率の推論基盤を提供し続ける

  1. 2027

    MN-Core L1000

    3D-Stacked DRAMにより、メモリ帯域のボトルネックを解消

  2. 2028

    MN-Core L2000

    さらなるバンド幅拡大へ

  3. 2030

    Next-Gen

06 — Contact