MA

mavis Q6 K

MavisGGUF by mikemoeUpdated 2024-11-20
Download on Hugging Face
Parameters1.24B
Context128K
Layers16
Architecturellama
Smallest quant1.0 GB
Quick answer

mavis Q6 K needs about 1.8 GB of memory at Q6_K (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.1 GB.

mavis Q6 K is a 1.24B-parameter Mavis model in GGUF format, quantized by mikemoe. Its trained context length is 128K tokens. The repository has 1 quant file, from 1.0 GB (Q6_K) to 1.0 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K1.0 GB 1.8 GB
Fits Get file →

What GPU do you need for mavis Q6 K?

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: the best quant that fits is Q6_K (1.0 GB file, about 1.8 GB in use).

Which mavis Q6 K quant should you choose?

Q6_K (1.0 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters1.24B
Layers16
Trained context131,072 tokens
KV cache (fp16)32 KB per token

Source

Quantized bymikemoe
FamilyMavis
Base modelmikemoe/mavis
Licensellama3.2
Downloads (HF)5
Last updated2024-11-20

Frequently asked questions about mavis Q6 K

How much VRAM does mavis Q6 K need?

About 1.8 GB at Q6_K with an 8K context window. That is the 1.0 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 mavis Q6 K on an 8 GB GPU?

Yes, with Q6_K: the 1.0 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mavis Q6 K GGUF?

It depends on the quant: Q6_K is 1.0 GB.

What context length does mavis Q6 K support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.1 GB at 32K.

Where can I download mavis Q6 K GGUF?

The files are on Hugging Face in the mikemoe/mavis-Q6_K-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 mavis Q6 K use?

Hugging Face lists the license as llama3.2. 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 mavis

Similar models

Browse all →

More from mikemoe

All by mikemoe →

More Mavis models

All Mavis →

Other tiny models

All tiny models →