LF

Luminium Gixel Cube v1

LfmGGUF by mambiuxUpdated 2026-05-31
Download on Hugging Face
Parameters426M
Context125K
Layers20
Architecturelfm2
Smallest quant0.3 GB
Quick answer

Luminium Gixel Cube v1 needs about 1.5 GB of memory at Q5_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.3 GB (Q5_K_M) to 0.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Luminium Gixel Cube v1 is a 426M-parameter Lfm model in GGUF format, quantized by mambiux. Its trained context length is 125K tokens. The repository has 2 quant files, from 0.3 GB (Q5_K_M) to 0.9 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M0.3 GB 1.5 GB
Fits Get file →
BF160.9 GB 2.0 GB
Fits Get file →

What GPU do you need for Luminium Gixel Cube v1?

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 (0.9 GB file, about 2.0 GB in use).

Which Luminium Gixel Cube v1 quant should you choose?

Q5_K_M (0.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelfm2
Parameters426M
Layers20
Trained context128,000 tokens
KV cache (fp16)80 KB per token

Source

Quantized bymambiux
FamilyLfm
Licenseapache-2.0
Downloads (HF)74
Last updated2026-05-31

Frequently asked questions about Luminium Gixel Cube v1

How much VRAM does Luminium Gixel Cube v1 need?

About 1.5 GB at Q5_K_M with an 8K context window. That is the 0.3 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 Luminium Gixel Cube v1 on an 8 GB GPU?

Yes, with BF16: the 0.9 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Luminium Gixel Cube v1 GGUF?

It depends on the quant: Q5_K_M is 0.3 GB, BF16 is 0.9 GB.

What context length does Luminium Gixel Cube v1 support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Luminium Gixel Cube v1 GGUF?

The files are on Hugging Face in the mambiux/Luminium-Gixel-Cube-v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Luminium Gixel Cube v1 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 LFM2-350M

Similar models

Browse all →

More from mambiux

All by mambiux →

More Lfm models

All Lfm →

Other tiny models

All tiny models →