MA

Mamba 370m Hf

MambaGGUF by 1bit-MONSTERUpdated 2026-09-26
Download on Hugging Face
Parameters372M
Context1024K
Layers48
Architecturemamba
Smallest quant0.7 GB
Quick answer

Mamba 370m Hf needs about 1.3 GB of memory at F16 (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Mamba 370m Hf is a 372M-parameter Mamba model in GGUF format, quantized by 1bit-MONSTER. Its trained context length is 1024K tokens. The repository has 1 quant file, from 0.7 GB (F16) to 0.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.7 GB 1.3 GB
Fits Get file →

What GPU do you need for Mamba 370m Hf?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is F16 (0.7 GB file, about 1.3 GB in use).

Which Mamba 370m Hf quant should you choose?

F16 (0.7 GB) is the middle option in this repository. 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

Architecturemamba
Parameters372M
Layers48
Trained context1,048,576 tokens

Source

Quantized by1bit-MONSTER
FamilyMamba
Licenseapache-2.0
Downloads (HF)58
Last updated2026-09-26

Frequently asked questions about Mamba 370m Hf

How much VRAM does Mamba 370m Hf need?

About 1.3 GB at F16 with an 8K context window. That is the 0.7 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 Mamba 370m Hf on an 8 GB GPU?

Yes, with F16: the 0.7 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mamba 370m Hf GGUF?

It depends on the quant: F16 is 0.7 GB.

What context length does Mamba 370m Hf support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download Mamba 370m Hf GGUF?

The files are on Hugging Face in the 1bit-MONSTER/Mamba-370M-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 Mamba 370m Hf 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.

Similar models

Browse all →

More from 1bit-MONSTER

All by 1bit-MONSTER →

More Mamba models

All Mamba →

Other tiny models

All tiny models →