IBM30BFP8 (Q4 est. ~12-15GB, unconfirmed) 下约 19 GB 显存

Granite 4.1 30B — 显存、速度与本地部署

作者: Jakub Rusinowski · 最后更新:

Largest Granite 4.1 tier — a hybrid Mamba2/attention design (interleaved SSM + attention layers), not MoE despite the 4.0 generation using MoE. ~18GB at FP8 (Q4 likely lower, ~12-15GB, unconfirmed). Context extendable to 512K. Apache 2.0.

Granite 4.1 30B 在 FP8 (Q4 est. ~12-15GB, unconfirmed) 下约需 19 GB 显存——量化权重加框架开销,不含 KV 缓存。在 Apple Silicon 上,这部分来自统一内存。

逻辑89
创意83
编程87

按量化级别的显存与速度

计算基准:NVIDIA RTX 4090 (24 GB)。仅含权重与开销:该模型架构未公开,因此未计入 KV 缓存。

量化显存速度(估算)适配
Q2_K
2.63 bpw
10.7 GB~61 tok/s可运行
Q3_K_M
3.41 bpw
13.6 GB~49 tok/s可运行
Q4_K_M
4.83 bpw
18.9 GB~37 tok/s可运行
Q5_K_M
5.67 bpw
22.1 GB~32 tok/s勉强
Q6_K
6.56 bpw
25.4 GB~4 tok/s需卸载
Q8_0
8.50 bpw
32.7 GB~3 tok/s需卸载
F16
16.00 bpw
60.8 GB—放不下

黑色标记 = NVIDIA RTX 4090 (24 GB) 上的可用显存。 估算来自内存带宽屋顶线模型,详见 方法说明页. Granite 4.1 30B 显存计算器 →

运行 Granite 4.1 30B

目录中能运行 Granite 4.1 30B 的最便宜 GPU 是 AMD Radeon RX 7900 XT (20 GB).

购买此硬件 AMD Radeon RX 7900 XT 20GB — 20 GB VRAM · 315 W board power立即云端部署 RunPod 上的 RTX 4090 — 低至 $0.34/小时 · 价格核实于 2026-07

或在 Vast.ai 比较,低至 $0.35/小时 (typical low · varies)

作为亚马逊联盟成员,我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金,您无需额外付费。

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。
AMD Radeon RX 7900 XT 20GB
20 GB VRAM · 315 W board power
2026年价格波动较大——请以当前商品页价格为准。

如何运行 Granite 4.1 30B

安装 Ollama,然后运行:

ollama run granite4.1:30b
Hugging Face 上的权重: ibm-granite/granite-4.1-30b ↗

规格

Verified — Checked against the primary source — the model card or the vendor spec page — and corroborated by a second independent source.

参数量
30 Billion
上下文窗口
128,000
架构
Hybrid Mamba2 + Attention (SSM)
提供商
IBM
许可证
Apache 2.0
规格量化
FP8 (Q4 est. ~12-15GB, unconfirmed)
系统内存
32 GB
记录更新于
2026-04-29
许可证Apache-2.0允许商业使用

Commercial use permitted. No usage restrictions beyond attribution.

质量与使用场景

评分由模型作者或独立评测方发布——衡量质量而非吞吐量,并非我们实测。

最适合enterpriselong contextreasoningmid range gpu

我的 GPU 能运行 Granite 4.1 30B 吗?

IBM Granite 4.1 的其他尺寸

Granite 4.1 30B — 常见问题

How much VRAM does Granite 4.1 30B need?

About 19 GB at FP8 (Q4 est. ~12-15GB, unconfirmed) — quantized weights plus framework overhead, before any KV cache. The cache grows with context length and is added on top; the table above folds it in. Apple Silicon counts unified memory toward the same figure.

Does Granite 4.1 30B run on an RTX 4090 (24 GB)?

Yes. Granite 4.1 30B needs about 19 GB at FP8 (Q4 est. ~12-15GB, unconfirmed), inside a 24 GB card, at an estimated 37 tokens/sec.

How do I run Granite 4.1 30B locally?

Install Ollama and run `ollama run granite4.1:30b`. That pulls the weights and starts a local OpenAI-compatible endpoint; after the download nothing leaves the machine.

What other sizes does IBM Granite 4.1 come in?

Granite 4.1 3B (3 GB), Granite 4.1 8B (6 GB), Granite 4.1 30B (19 GB). Every size shares the family's training and licence; the larger ones score higher and need proportionally more memory.