MF

MFANN3bv0.18

MfannGGUF by netcat420Updated 2024-07-25
Download on Hugging Face
Parameters2.78B
Context32K
Layers32
Architecturephi2
Smallest quant1.6 GB
Quick answer

MFANN3bv0.18 needs about 4.8 GB of memory at its main file (a 1.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 1.6 GB to 1.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

MFANN3bv0.18 is a 2.78B-parameter Mfann model in GGUF format, quantized by netcat420. Its trained context length is 32K tokens. The repository has 2 quant files, from 1.6 GB to 1.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.6 GB 4.8 GB
Fits Get file →
—1.7 GB 4.9 GB
Fits Get file →

What GPU do you need for MFANN3bv0.18?

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: the best quant that fits is the main file (1.7 GB file, about 4.9 GB in use).

Specifications

Architecture from the GGUF header

Architecturephi2
Parameters2.78B
Layers32
Trained context32,768 tokens
KV cache (fp16)320 KB per token

Source

Quantized bynetcat420
FamilyMfann
Licensemit
Downloads (HF)6
Last updated2024-07-25

Frequently asked questions about MFANN3bv0.18

How much VRAM does MFANN3bv0.18 need?

About 4.8 GB at its main file 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 MFANN3bv0.18 on an 8 GB GPU?

Yes, with the smaller files: the 1.7 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MFANN3bv0.18 GGUF?

It depends on the quant: file is 1.6 GB, file is 1.7 GB.

What context length does MFANN3bv0.18 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download MFANN3bv0.18 GGUF?

The files are on Hugging Face in the netcat420/MFANN3bv0.18-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 MFANN3bv0.18 use?

Hugging Face lists the license as mit. 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 netcat420

All by netcat420 →

More Mfann models

All Mfann →

Other tiny models

All tiny models →