MA

MambaHermes 3B

MambahermesGGUF by mradermacherUpdated 2024-12-20
Download on Hugging Face
Parameters2.77B
Context1024K
Layers64
Architecturemamba
Smallest quant1.0 GB
Quick answer

MambaHermes 3B needs about 2.3 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.0 GB (Q2_K) to 5.6 GB (F16).

MambaHermes 3B is a 2.77B-parameter Mambahermes model in GGUF format, quantized by mradermacher. Its trained context length is 1024K tokens. The repository has 12 quant files, from 1.0 GB (Q2_K) to 5.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.0 GB 1.6 GB
Fits Get file →
Q3_K_L1.3 GB 1.9 GB
Fits Get file →
Q3_K_M1.3 GB 1.9 GB
Fits Get file →
Q3_K_S1.3 GB 1.9 GB
Fits Get file →
IQ4_XS1.5 GB 2.2 GB
Fits Get file →
Q4_K_M1.6 GB 2.3 GB
Fits Get file →
Q4_K_S1.6 GB 2.3 GB
Fits Get file →
Q5_K_M2.0 GB 2.7 GB
Fits Get file →
Q5_K_S2.0 GB 2.7 GB
Fits Get file →
Q6_K2.3 GB 3.1 GB
Fits Get file →
Q8_03.0 GB 3.8 GB
Fits Get file →
F165.6 GB 6.7 GB
Fits Get file →

What GPU do you need for MambaHermes 3B?

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 Q8_0 (3.0 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 3.8 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.6 GB file, about 6.7 GB in use).

Which MambaHermes 3B quant should you choose?

Q4_K_M is the usual starting point for MambaHermes 3B: it balances file size and quality well. Here it is a 1.6 GB file.

The Q8_0 file is 3.0 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 1.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemamba
Parameters2.77B
Layers64
Trained context1,048,576 tokens

Source

Quantized bymradermacher
Licensewtfpl
Downloads (HF)175
Last updated2024-12-20

Frequently asked questions about MambaHermes 3B

How much VRAM does MambaHermes 3B need?

About 2.3 GB at Q4_K_M with an 8K context window. That is the 1.6 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 MambaHermes 3B on an 8 GB GPU?

Yes, with F16: the 5.6 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MambaHermes 3B GGUF?

It depends on the quant: Q2_K is 1.0 GB, Q3_K_L is 1.3 GB, Q3_K_M is 1.3 GB, Q3_K_S is 1.3 GB, IQ4_XS is 1.5 GB, Q4_K_M is 1.6 GB and 6 more.

What context length does MambaHermes 3B support?

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

Where can I download MambaHermes 3B GGUF?

The files are on Hugging Face in the mradermacher/MambaHermes-3B-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 MambaHermes 3B use?

Hugging Face lists the license as wtfpl. 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 MambaHermes-3B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mambahermes models

All Mambahermes →

Other tiny models

All tiny models →