GR

lumynax infused granite31 1b a400m

GraniteGGUF by AbteeXAILabUpdated 2026-09-03
Download on Hugging Face
Parameters1.33B
Context128K
Layers24
Architecturegranitemoe
Smallest quant0.8 GB
Quick answer

lumynax infused granite31 1b a400m needs about 1.7 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

lumynax infused granite31 1b a400m is a 1.33B-parameter Granite model in GGUF format, quantized by AbteeXAILab. Its trained context length is 128K tokens. The repository has 1 quant file, from 0.8 GB (Q4_K_M) to 0.8 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.8 GB 1.7 GB
Fits Get file →

What GPU do you need for lumynax infused granite31 1b a400m?

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 Q4_K_M (0.8 GB file, about 1.7 GB in use).

Which lumynax infused granite31 1b a400m quant should you choose?

Q4_K_M is the usual starting point for lumynax infused granite31 1b a400m: it balances file size and quality well. Here it is a 0.8 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranitemoe
Parameters1.33B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized byAbteeXAILab
FamilyGranite
Licenseapache-2.0
Downloads (HF)50
Last updated2026-09-03

Frequently asked questions about lumynax infused granite31 1b a400m

How much VRAM does lumynax infused granite31 1b a400m need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 0.8 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 lumynax infused granite31 1b a400m on an 8 GB GPU?

Yes, with Q4_K_M: the 0.8 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of lumynax infused granite31 1b a400m GGUF?

It depends on the quant: Q4_K_M is 0.8 GB.

What context length does lumynax infused granite31 1b a400m support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download lumynax infused granite31 1b a400m GGUF?

The files are on Hugging Face in the AbteeXAILab/lumynax-infused-granite31-1b-a400m-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 lumynax infused granite31 1b a400m 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.

Other GGUFs of granite-3.1-1b-a400m-instruct

Similar models

Browse all →

More from AbteeXAILab

All by AbteeXAILab →

More Granite models

All Granite →

Other tiny models

All tiny models →