IBM

Granite 4.1 3B

当前

HuggingFace

Ollama

77.4K下载量73点赞Apr 2026发布日期131K tokens上下文Apache 2.0许可证42 基础质量

Granite 4.1 3B (3B parameters) requires approximately 4.9 GB of VRAM with Q4_K_M quantization. For the best balance of quality and speed, we recommend hardware with at least 6 GB of VRAM.

快速开始

— 复制粘贴即可本地运行

Copy-paste commands to run Granite 4.1 3B on your machine.

Run

ollama run granite4.1:3b

Quick specs

Parameters3B

Architecturedense

Context131K tokens

Modalitytext

Min RAM1.2 GB

Rec. RAM1.8 GB (Q4_K_M)

LicenseApache 2.0

FamilyGranite

✓ Code✓ Chat✓ RAG

About this model

Granite 4.1 3B is IBM's smallest Granite 4.1 dense decoder-only model, trained on roughly 15T tokens with 128K context. Apache 2.0 licensed and tuned for fast, commercially-friendly RAG, coding, and assistant workloads on small GPUs.

•Dense decoder-only 3B — runs on 8 GB GPUs at Q8 or BF16
•Apache 2.0 license for commercial RAG and assistant use
•128K context for long-document retrieval

Granite 4.1 3B 的最佳选择

Intel Arc Pro A40 6GBA

运行此模型

Granite 4.1 3B on RTX 4050 Laptop 6GB Granite 4.1 3B on RTX 2060 6GB Granite 4.1 3B on Intel Arc Pro A40 6GB

量化选项

各量化级别的 VRAM 估算

No hardware detected — fit column shows raw VRAM estimates

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	1.2 GB	Low	—
Q3_K_S	3	1.5 GB	Low	—
NVFP4	4	1.7 GB	Medium	—
Q4_K_M	4	1.8 GB	Medium	—
Q5_K_M	5	2.2 GB	High	—
Q6_K	6	2.5 GB	High	—
Q8_0	8	3.2 GB	Very High	—
F16	16	6.1 GB	Maximum	—

硬件兼容性

全部硬件的适配估算

打开计算器

Computing compatibility...

内存详细分析

Reference: RTX 2060 6GB

Weights1.8 GB

KV Cache1.2 GB

Runtime1.2 GB

Headroom0.6 GB

常见问题

FAQ — Granite 4.1 3B

另请参阅

量化指南评分方法打开计算器