MA

Mars_27B_V.1

MarsGGUF by OddTheGreatUpdated 2025-11-11
Download on Hugging Face
Parameters28.4B
Context128K
Layers62
Architecturegemma3
Smallest quant16.5 GB
Quick answer

Mars_27B_V.1 needs about 21.1 GB of memory at Q4_K_S (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.

Mars_27B_V.1 is a 28.4B-parameter Mars model in GGUF format, quantized by OddTheGreat. Its trained context length is 128K tokens. The repository has 1 quant file, from 16.5 GB (Q4_K_S) to 16.5 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S16.5 GB 21.1 GB
Too big Get file →

What GPU do you need for Mars_27B_V.1?

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_S (16.5 GB file, about 21.1 GB in use).

Which Mars_27B_V.1 quant should you choose?

Q4_K_S (16.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters28.4B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized byOddTheGreat
FamilyMars
Downloads (HF)12
Last updated2025-11-11

Frequently asked questions about Mars_27B_V.1

How much VRAM does Mars_27B_V.1 need?

About 21.1 GB at Q4_K_S 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 Mars_27B_V.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mars_27B_V.1 GGUF?

It depends on the quant: Q4_K_S is 16.5 GB.

What context length does Mars_27B_V.1 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 Mars_27B_V.1 GGUF?

The files are on Hugging Face in the OddTheGreat/Mars_27B_V.1-Q4_K_S-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 Mars_27B_V.1

Similar models

Browse all →

More from OddTheGreat

All by OddTheGreat →

More Mars models

All Mars →

Other medium models

All medium models →