MM

mmlu eval models

MmluGGUF by elichen-skymizerUpdated 2026-03-26
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant13.5 GB
Quick answer

mmlu eval models needs about 18.3 GB of memory at its main file (a 13.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 13.5 GB (BF16) to 13.5 GB (F32).

mmlu eval models is a 6.74B-parameter Mmlu model in GGUF format, quantized by elichen-skymizer. Its trained context length is 4K tokens. The repository has 6 quant files, from 13.5 GB (BF16) to 13.5 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1613.5 GB 16.1 GB
Too big Get file →
BF1613.5 GB 16.1 GB
Too big Get file →
—13.5 GB 16.1 GB
Too big Get file →
—13.5 GB 16.1 GB
Too big Get file →
—13.5 GB 16.1 GB
Too big Get file →
F3213.5 GB 16.1 GB
Too big Get file →

What GPU do you need for mmlu eval models?

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 BF16 (13.5 GB file, about 18.3 GB in use).

Which mmlu eval models quant should you choose?

If memory is tight, the smallest file is BF16 at 13.5 GB, with the quality trade-offs that come with fewer bits. 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

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byelichen-skymizer
FamilyMmlu
Downloads (HF)71
Last updated2026-03-26

Frequently asked questions about mmlu eval models

How much VRAM does mmlu eval models need?

About 18.3 GB at its main file with an 8K context window. That is the 13.5 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 mmlu eval models on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mmlu eval models GGUF?

It depends on the quant: BF16 is 13.5 GB, BF16 is 13.5 GB, file is 13.5 GB, file is 13.5 GB, file is 13.5 GB, F32 is 13.5 GB.

What context length does mmlu eval models support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download mmlu eval models GGUF?

The files are on Hugging Face in the elichen-skymizer/mmlu-eval-models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from elichen-skymizer

All by elichen-skymizer →

More Mmlu models

All Mmlu →

Other small models

All small models →