MI

Mimma 3 27b

MimmaGGUF by pankajmathurUpdated 2025-12-10
Download on Hugging Face
Parameters27B
Context128K
Layers62
Architecturegemma3
Smallest quant16.5 GB
Quick answer

Mimma 3 27b needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

Mimma 3 27b is a 27B-parameter Mimma model in GGUF format, quantized by pankajmathur. Its trained context length is 128K tokens. The repository has 1 quant file, from 16.5 GB (Q4_K_M) to 16.5 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M16.5 GB 21.2 GB
Too big Get file →

What GPU do you need for Mimma 3 27b?

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 (16.5 GB file, about 21.2 GB in use).

Which Mimma 3 27b quant should you choose?

Q4_K_M is the usual starting point for Mimma 3 27b: it balances file size and quality well. Here it is a 16.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters27B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized bypankajmathur
FamilyMimma
Licensegemma
Downloads (HF)34
Last updated2025-12-10

Frequently asked questions about Mimma 3 27b

How much VRAM does Mimma 3 27b need?

About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Mimma 3 27b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mimma 3 27b GGUF?

It depends on the quant: Q4_K_M is 16.5 GB.

What context length does Mimma 3 27b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.

Where can I download Mimma 3 27b GGUF?

The files are on Hugging Face in the pankajmathur/Mimma-3-27b-Q4_K_M-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 Mimma 3 27b 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.

Other GGUFs of Mimma-3-27b

Similar models

Browse all →

More from pankajmathur

All by pankajmathur →

More Mimma models

All Mimma →

Other medium models

All medium models →