MA

marin 8b base Q8 0

MarinGGUF by jessicataUpdated 2025-05-19
Download on Hugging Face
Parameters8.03B
Context4K
Layers32
Architecturellama
Smallest quant8.5 GB
Quick answer

marin 8b base Q8 0 needs about 10.1 GB of memory at Q8_0 (a 8.5 GB file) with an 8K context window, so it fits on a 12 GB GPU.

marin 8b base Q8 0 is a 8.03B-parameter Marin model in GGUF format, quantized by jessicata. Its trained context length is 4K tokens. The repository has 1 quant file, from 8.5 GB (Q8_0) to 8.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_08.5 GB 9.6 GB
Too big Get file →

What GPU do you need for marin 8b base Q8 0?

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: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).

Which marin 8b base Q8 0 quant should you choose?

Q8_0 (8.5 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized byjessicata
FamilyMarin
Licenseapache-2.0
Downloads (HF)7
Last updated2025-05-19

Frequently asked questions about marin 8b base Q8 0

How much VRAM does marin 8b base Q8 0 need?

About 10.1 GB at Q8_0 with an 8K context window. That is the 8.5 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 marin 8b base Q8 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of marin 8b base Q8 0 GGUF?

It depends on the quant: Q8_0 is 8.5 GB.

What context length does marin 8b base Q8 0 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download marin 8b base Q8 0 GGUF?

The files are on Hugging Face in the jessicata/marin-8b-base-Q8_0-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 marin 8b base Q8 0 use?

Hugging Face lists the license as apache-2.0. 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 marin-8b-base

Similar models

Browse all →

More from jessicata

All by jessicata →

More Marin models

All Marin →

Other small models

All small models →