FI

fialka 7B v3

FialkaGGUF by AndreyRGWUpdated 2024-02-01
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant4.1 GB
Quick answer

fialka 7B v3 needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU.

fialka 7B v3 is a 6.74B-parameter Fialka model in GGUF format, quantized by AndreyRGW. Its trained context length is 4K tokens. The repository has 1 quant file, from 4.1 GB (Q4_K_M) to 4.1 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.1 GB 6.7 GB
Fits Get file →

What GPU do you need for fialka 7B v3?

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: the best quant that fits is Q4_K_M (4.1 GB file, about 8.9 GB in use).

Which fialka 7B v3 quant should you choose?

Q4_K_M is the usual starting point for fialka 7B v3: it balances file size and quality well. Here it is a 4.1 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byAndreyRGW
FamilyFialka
Licenseapache-2.0
Downloads (HF)10
Last updated2024-02-01

Frequently asked questions about fialka 7B v3

How much VRAM does fialka 7B v3 need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 fialka 7B v3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of fialka 7B v3 GGUF?

It depends on the quant: Q4_K_M is 4.1 GB.

What context length does fialka 7B v3 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download fialka 7B v3 GGUF?

The files are on Hugging Face in the AndreyRGW/fialka-7B-v3-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 fialka 7B v3 use?

Hugging Face lists the license as apache-2.0. 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 AndreyRGW

All by AndreyRGW →

More Fialka models

All Fialka →

Other small models

All small models →