AR

arbiter v4 12b

ArbiterGGUF by hiteshlukeUpdated 2026-10-29
Download on Hugging Face
Parameters12.9B
Context256K
Layers48
Architecturegemma4
Smallest quant7.9 GB
Quick answer

arbiter v4 12b needs about 21.3 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 7.9 GB (Q4_K_M) to 13.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

arbiter v4 12b is a 12.9B-parameter Arbiter model in GGUF format, quantized by hiteshluke. Its trained context length is 256K tokens. The repository has 2 quant files, from 7.9 GB (Q4_K_M) to 13.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M7.9 GB 21.3 GB
Too big Get file →
Q8_013.7 GB 27.1 GB
Too big Get file →

What GPU do you need for arbiter v4 12b?

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: the best quant that fits is Q4_K_M (7.9 GB file, about 21.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (13.7 GB file, about 27.1 GB in use).

Which arbiter v4 12b quant should you choose?

Q4_K_M is the usual starting point for arbiter v4 12b: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters12.9B
Layers48
Trained context262,144 tokens
KV cache (fp16)1536 KB per token

Source

Quantized byhiteshluke
FamilyArbiter
Licensegemma
Downloads (HF)127
Last updated2026-10-29

Frequently asked questions about arbiter v4 12b

How much VRAM does arbiter v4 12b need?

About 21.3 GB at Q4_K_M with an 8K context window. That is the 7.9 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 arbiter v4 12b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of arbiter v4 12b GGUF?

It depends on the quant: Q4_K_M is 7.9 GB, Q8_0 is 13.7 GB.

What context length does arbiter v4 12b support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.

Where can I download arbiter v4 12b GGUF?

The files are on Hugging Face in the hiteshluke/arbiter-v4-12b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does arbiter v4 12b use?

Hugging Face lists the license as gemma. 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 hiteshluke

All by hiteshluke →

More Arbiter models

All Arbiter →

Other medium models

All medium models →