MI

MiS Firefly v0.2 22B

MisGGUF by invisietchUpdated 2024-11-07
Download on Hugging Face
Parameters22.2B
Context32K
Layers56
Architecturellama
Smallest quant18.3 GB
Quick answer

MiS Firefly v0.2 22B needs about 20.6 GB of memory at Q6_K (a 18.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

MiS Firefly v0.2 22B is a 22.2B-parameter Mis model in GGUF format, quantized by invisietch. Its trained context length is 32K tokens. The repository has 1 quant file, from 18.3 GB (Q6_K) to 18.3 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K18.3 GB 20.6 GB
Too big Get file →

What GPU do you need for MiS Firefly v0.2 22B?

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: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q6_K (18.3 GB file, about 20.6 GB in use).

Which MiS Firefly v0.2 22B quant should you choose?

Q6_K (18.3 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
Parameters22.2B
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized byinvisietch
FamilyMis
Licenseother
Downloads (HF)4
Last updated2024-11-07

Frequently asked questions about MiS Firefly v0.2 22B

How much VRAM does MiS Firefly v0.2 22B need?

About 20.6 GB at Q6_K with an 8K context window. That is the 18.3 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 MiS Firefly v0.2 22B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MiS Firefly v0.2 22B GGUF?

It depends on the quant: Q6_K is 18.3 GB.

What context length does MiS Firefly v0.2 22B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download MiS Firefly v0.2 22B GGUF?

The files are on Hugging Face in the invisietch/MiS-Firefly-v0.2-22B-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 MiS Firefly v0.2 22B use?

Hugging Face lists the license as other. 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 invisietch

All by invisietch →

More Mis models

All Mis →

Other medium models

All medium models →