MH

MHA FF V02

MhaGGUF by RawrWoofMeowUpdated 2024-11-29
Download on Hugging Face
Parameters8.03B
Context49K
Layers—
Architecturellama
Smallest quant4.9 GB
Quick answer

MHA FF V02 needs about 6.0 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 4.9 GB (Q4_K_M) to 16.1 GB (BF16).

MHA FF V02 is a 8.03B-parameter Mha model in GGUF format, quantized by RawrWoofMeow. Its trained context length is 49K tokens. The repository has 2 quant files, from 4.9 GB (Q4_K_M) to 16.1 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.9 GB 6.0 GB
Fits Get file →
BF1616.1 GB 18.5 GB
Too big Get file →

What GPU do you need for MHA FF V02?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q4_K_M (4.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (4.9 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (4.9 GB file, about 6.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (4.9 GB file, about 6.0 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.1 GB file, about 18.5 GB in use).

Which MHA FF V02 quant should you choose?

Q4_K_M is the usual starting point for MHA FF V02: it balances file size and quality well. Here it is a 4.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Trained context50,000 tokens

Source

Quantized byRawrWoofMeow
FamilyMha
Licenseunlicense
Downloads (HF)0
Last updated2024-11-29

Frequently asked questions about MHA FF V02

How much VRAM does MHA FF V02 need?

About 6.0 GB at Q4_K_M with an 8K context window. That is the 4.9 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 MHA FF V02 on an 8 GB GPU?

Yes, with Q4_K_M: the 4.9 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MHA FF V02 GGUF?

It depends on the quant: Q4_K_M is 4.9 GB, BF16 is 16.1 GB.

What context length does MHA FF V02 support?

The GGUF header lists a trained context length of 50,000 tokens (49K).

Where can I download MHA FF V02 GGUF?

The files are on Hugging Face in the RawrWoofMeow/MHA-FF-V02 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does MHA FF V02 use?

Hugging Face lists the license as unlicense. 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 RawrWoofMeow

All by RawrWoofMeow →

More Mha models

All Mha →

Other small models

All small models →