GR

granite-3.0-1b-a400m-base

GraniteGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters1.38B
Context4K
Layers24
Architecturegranitemoe
Smallest quant0.6 GB
Quick answer

granite-3.0-1b-a400m-base needs about 1.8 GB of memory at Q4_1 (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.6 GB (IQ3_XXS) to 2.8 GB (BF16).

granite-3.0-1b-a400m-base is a 1.38B-parameter Granite model in GGUF format, quantized by Mungert. Its trained context length is 4K tokens. The repository has 19 quant files, from 0.6 GB (IQ3_XXS) to 2.8 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS0.6 GB 1.3 GB
Fits Get file →
IQ3_XS0.6 GB 1.3 GB
Fits Get file →
IQ3_M0.6 GB 1.3 GB
Fits Get file →
IQ3_S0.6 GB 1.3 GB
Fits Get file →
Q3_K_S0.7 GB 1.4 GB
Fits Get file →
Q3_K_M0.7 GB 1.4 GB
Fits Get file →
IQ4_XS0.8 GB 1.5 GB
Fits Get file →
Q4_00.8 GB 1.5 GB
Fits Get file →
IQ4_NL0.8 GB 1.5 GB
Fits Get file →
Q4_10.9 GB 1.6 GB
Fits Get file →
Q5_01.0 GB 1.7 GB
Fits Get file →
Q5_K_S1.0 GB 1.7 GB
Fits Get file →
Q5_K_M1.0 GB 1.7 GB
Fits Get file →
Q5_11.0 GB 1.7 GB
Fits Get file →
Q6_K_M1.1 GB 1.8 GB
Fits Get file →
Q8_01.5 GB 2.2 GB
Fits Get file →
BF161.6 GB 2.3 GB
Fits Get file →
F161.6 GB 2.3 GB
Fits Get file →
BF162.8 GB 3.5 GB
Fits Get file →

What GPU do you need for granite-3.0-1b-a400m-base?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is BF16 (2.8 GB file, about 3.7 GB in use).

Which granite-3.0-1b-a400m-base quant should you choose?

Q4_1 (0.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is IQ3_XXS at 0.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranitemoe
Parameters1.38B (approximate, mixture of experts)
Layers24
Trained context4,096 tokens
KV cache (fp16)48 KB per token

Source

Quantized byMungert
FamilyGranite
Licenseapache-2.0
Downloads (HF)310
Last updated2025-09-24

Frequently asked questions about granite-3.0-1b-a400m-base

How much VRAM does granite-3.0-1b-a400m-base need?

About 1.8 GB at Q4_1 with an 8K context window. That is the 0.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run granite-3.0-1b-a400m-base on an 8 GB GPU?

Yes, with BF16: the 2.8 GB file needs about 3.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of granite-3.0-1b-a400m-base GGUF?

It depends on the quant: IQ3_XXS is 0.6 GB, IQ3_XS is 0.6 GB, IQ3_M is 0.6 GB, IQ3_S is 0.6 GB, Q3_K_S is 0.7 GB, Q3_K_M is 0.7 GB and 13 more.

What context length does granite-3.0-1b-a400m-base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.2 GB at 4K.

Where can I download granite-3.0-1b-a400m-base GGUF?

The files are on Hugging Face in the Mungert/granite-3.0-1b-a400m-base-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does granite-3.0-1b-a400m-base use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from Mungert

All by Mungert →

More Granite models

All Granite →

Other tiny models

All tiny models →