IN

inkling reap128 magicpack

InklingGGUF by nbKPSUpdated 2026-11-01
Download on Hugging Face
Parameters135B
Context1024K
Layers42
Architectureinkling
Smallest quant36.3 GB
Quick answer

inkling reap128 magicpack needs about 65.5 GB of memory at its main file (a 59.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 36.3 GB (IQ1_M) to 74.8 GB (MXFP4). Longer context needs more: at 32K tokens the KV cache alone adds about 22.5 GB.

inkling reap128 magicpack is a 135B-parameter Inkling model in GGUF format, quantized by nbKPS. Its trained context length is 1024K tokens. The repository has 3 quant files, from 36.3 GB (IQ1_M) to 74.8 GB (MXFP4).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_M36.3 GB (6 parts) 42.4 GB
Too big Get file →
—59.3 GB (6 parts) 65.5 GB
Too big Get file →
MXFP474.8 GB (6 parts) 81.0 GB
Too big Get file →

What GPU do you need for inkling reap128 magicpack?

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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is IQ1_M (36.3 GB file, about 42.4 GB in use).

Which inkling reap128 magicpack quant should you choose?

If memory is tight, the smallest file is IQ1_M at 36.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureinkling
Parameters135B (approximate, mixture of experts)
Layers42
Trained context1,048,576 tokens
KV cache (fp16)672 KB per token

Source

Quantized bynbKPS
FamilyInkling
Licenseother
Downloads (HF)512
Last updated2026-11-01

Frequently asked questions about inkling reap128 magicpack

How much VRAM does inkling reap128 magicpack need?

About 65.5 GB at its main file with an 8K context window. That is the 59.3 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 inkling reap128 magicpack on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 42.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of inkling reap128 magicpack GGUF?

It depends on the quant: IQ1_M is 36.3 GB, file is 59.3 GB, MXFP4 is 74.8 GB.

What context length does inkling reap128 magicpack support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 5.6 GB at 8K and 22.5 GB at 32K.

Where can I download inkling reap128 magicpack GGUF?

The files are on Hugging Face in the nbKPS/inkling-reap128-magicpack-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 inkling reap128 magicpack use?

Hugging Face lists the license as other. 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 nbKPS

All by nbKPS →

More Inkling models

All Inkling →

Other large models

All large models →