GR

Apriel 1.5 15b Thinker Unsloth

GraniteGGUF by magiccodingmanUpdated 2026-04-25
Download on Hugging Face
Parameters14.4B
Context256K
Layers48
Architecturellama
Smallest quant13.1 GB
Quick answer

Apriel 1.5 15b Thinker Unsloth needs about 15.2 GB of memory at MXFP4_MOE (a 13.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Apriel 1.5 15b Thinker Unsloth is a 14.4B-parameter Granite model in GGUF format, quantized by magiccodingman. Its trained context length is 256K tokens. The repository has 1 quant file, from 13.1 GB (MXFP4_MOE) to 13.1 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE13.1 GB 15.2 GB
Too big Get file →

What GPU do you need for Apriel 1.5 15b Thinker Unsloth?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is MXFP4_MOE (13.1 GB file, about 15.2 GB in use).

Which Apriel 1.5 15b Thinker Unsloth quant should you choose?

MXFP4_MOE (13.1 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters14.4B
Layers48
Trained context262,400 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymagiccodingman
FamilyGranite
Licensemit
Downloads (HF)83
Last updated2026-04-25

Frequently asked questions about Apriel 1.5 15b Thinker Unsloth

How much VRAM does Apriel 1.5 15b Thinker Unsloth need?

About 15.2 GB at MXFP4_MOE with an 8K context window. That is the 13.1 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 Apriel 1.5 15b Thinker Unsloth on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Apriel 1.5 15b Thinker Unsloth GGUF?

It depends on the quant: MXFP4_MOE is 13.1 GB.

What context length does Apriel 1.5 15b Thinker Unsloth support?

The GGUF header lists a trained context length of 262,400 tokens (256K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Apriel 1.5 15b Thinker Unsloth GGUF?

The files are on Hugging Face in the magiccodingman/Apriel-1.5-15b-Thinker-Unsloth-MXFP4-Hybrid-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 Apriel 1.5 15b Thinker Unsloth use?

Hugging Face lists the license as mit. 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-4.0-h-1b

Similar models

Browse all →

More from magiccodingman

All by magiccodingman →

More Granite models

All Granite →

Other medium models

All medium models →