Granite 4.1: IBM's 8B Model Matching 32B MoE
IBM has released Granite 4.1, a family of open-source language models designed for enterprise use, featuring three sizes and trained on 15 trillion tokens. The 8B model utilizes a dense architecture without mixture of experts (MoE) techniques and outperforms Granite 4.0-H-Small across various benchmarks.
firethering.com
9 min
1d ago
Granite 4.1: IBM's 8B Model Matching 32B MoE
IBM has released Granite 4.1, a family of open-source language models designed for enterprise use, featuring three sizes and trained on 15 trillion tokens. The 8B model utilizes a dense architecture without mixture of experts (MoE) techniques and outperforms Granite 4.0-H-Small across various benchmarks.
firethering.com
9 min
1d ago
Granite 4.1: IBM's 8B Model Matching 32B MoE
IBM has released Granite 4.1, a family of open-source language models designed for enterprise use, featuring three sizes and trained on 15 trillion tokens. The 8B model utilizes a dense architecture without mixture of experts (MoE) techniques and outperforms Granite 4.0-H-Small across various benchmarks.
firethering.com
9 min
1d ago
No more articles to load