SP

Spartan 1.2 2B MLX

SpartanGGUF by IlidesUpdated 2026-08-03
Download on Hugging Face
Parameters1.88B
Context256K
Layers24
Architectureqwen35
Smallest quant3.8 GB
Quick answer

Spartan 1.2 2B MLX needs about 4.7 GB of memory at F16 (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Spartan 1.2 2B MLX is a 1.88B-parameter Spartan model in GGUF format, quantized by Ilides. Its trained context length is 256K tokens. The repository has 1 quant file, from 3.8 GB (F16) to 3.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F163.8 GB 4.7 GB
Fits Get file →

What GPU do you need for Spartan 1.2 2B MLX?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is F16 (3.8 GB file, about 4.7 GB in use).

Which Spartan 1.2 2B MLX quant should you choose?

F16 (3.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters1.88B
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byIlides
FamilySpartan
Licenseapache-2.0
Downloads (HF)6
Last updated2026-08-03

Frequently asked questions about Spartan 1.2 2B MLX

How much VRAM does Spartan 1.2 2B MLX need?

About 4.7 GB at F16 with an 8K context window. That is the 3.8 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 Spartan 1.2 2B MLX on an 8 GB GPU?

Yes, with F16: the 3.8 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Spartan 1.2 2B MLX GGUF?

It depends on the quant: F16 is 3.8 GB.

What context length does Spartan 1.2 2B MLX support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Spartan 1.2 2B MLX GGUF?

The files are on Hugging Face in the Ilides/Spartan-1.2-2B-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 Spartan 1.2 2B MLX 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 Ilides

All by Ilides →

More Spartan models

All Spartan →

Other tiny models

All tiny models →