IBM Granite 4.2 — IBM 的本地 AI 模型

作者: Jakub Rusinowski · 最后更新:

IBM's first family of dense decoder-only reasoning models, released August 2026 in 3B, 8B and 30B. Granite 4.2 drops the hybrid Mamba-2 MoE design of Granite 4.0 and continues the dense line Granite 4.1 started. Each size is pretrained from scratch on roughly 15T tokens with a five-phase context extension to 512K, then RL-post-trained for tool calling, RAG, structured JSON and an explicit thinking mode. All three are Apache 2.0.

变体

IBM Granite 4.2 最小的变体在 Q4_K_M 下约需 3 GB 显存——量化权重加框架开销,不含 KV 缓存。

模型显存
Granite 4.2 3B →
3B
~2.6 GB
Granite 4.2 8B →
8B
~5.6 GB
Granite 4.2 30B →
30B
~18.9 GB

显存为 Q4_K_M 下的量化权重加开销,与 GPU 与显存检测器使用同一引擎计算。

如何在本地运行 IBM Granite 4.2

安装 Ollama,然后拉取标签。

ollama run granite4.2:3b

在上方选择一个尺寸,查看它自己的显存、速度估算和安装命令。

许可证

Apache-2.0允许商业使用

Commercial use permitted. No usage restrictions beyond attribution.

适用于: Granite 4.2 3B, Granite 4.2 8B, Granite 4.2 30B

推荐 GPU

目录中能在本地运行 IBM Granite 4.2(至少 3 GB 显存)的最便宜 GPU 是 Intel Arc B570 (10 GB).

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买,LLM Configurator 可能会获得佣金,而你无需支付任何额外费用。作为亚马逊联盟成员(Amazon Associate),LLM Configurator 会从符合条件的购买中获得收益。
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026年价格波动较大——请以当前商品页价格为准。

我的 GPU 能运行 IBM Granite 4.2 吗?

IBM Granite 4.2 — 常见问题

How much VRAM does IBM Granite 4.2 need?

IBM Granite 4.2 needs about 3 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Granite 4.2 3B (3 GB, Q4_K_M); Granite 4.2 8B (6 GB, Q4_K_M); Granite 4.2 30B (19 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run IBM Granite 4.2 on an RTX 4090 (24 GB)?

Yes — IBM Granite 4.2 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.

What quantization should I use for IBM Granite 4.2?

Q4_K_M is the best balance of quality and VRAM for IBM Granite 4.2 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.

How do I run IBM Granite 4.2 with Ollama?

Install Ollama, then run: ollama run granite4.2:3b. This downloads IBM Granite 4.2 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.