AN

Anthrobomination 70B IK

AnthrobominationGGUF by MawdisticalUpdated 2025-08-04
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant28.2 GB
Quick answer

Anthrobomination 70B IK needs about 38.8 GB of memory at its main file (a 35.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 8 quants, from 28.2 GB to 40.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Anthrobomination 70B IK is a 70.6B-parameter Anthrobomination model in GGUF format, quantized by Mawdistical. Its trained context length is 128K tokens. The repository has 8 quant files, from 28.2 GB to 40.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—28.2 GB 31.3 GB
Too big Get file →
—28.4 GB 31.6 GB
Too big Get file →
—30.8 GB 34.0 GB
Too big Get file →
—35.7 GB 38.8 GB
Too big Get file →
—35.7 GB 38.8 GB
Too big Get file →
—37.8 GB 41.0 GB
Too big Get file →
—37.8 GB 41.0 GB
Too big Get file →
—40.0 GB 43.2 GB
Too big Get file →

What GPU do you need for Anthrobomination 70B IK?

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: the best quant that fits is the main file (28.4 GB file, about 31.6 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (40.0 GB file, about 43.2 GB in use).

Which Anthrobomination 70B IK quant should you choose?

If memory is tight, the smallest file is the first one in the table at 28.2 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byMawdistical
Downloads (HF)46
Last updated2025-08-04

Frequently asked questions about Anthrobomination 70B IK

How much VRAM does Anthrobomination 70B IK need?

About 38.8 GB at its main file with an 8K context window. That is the 35.7 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 Anthrobomination 70B IK on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 31.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Anthrobomination 70B IK GGUF?

It depends on the quant: file is 28.2 GB, file is 28.4 GB, file is 30.8 GB, file is 35.7 GB, file is 35.7 GB, file is 37.8 GB and 2 more.

What context length does Anthrobomination 70B IK support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Anthrobomination 70B IK GGUF?

The files are on Hugging Face in the Mawdistical/Anthrobomination-70B-IK-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Anthrobomination-70B

Similar models

Browse all →

More from Mawdistical

All by Mawdistical →

More Anthrobomination models

All Anthrobomination →

Other large models

All large models →