NI

Ninja V3

NinjaGGUF by MaziyarPanahiUpdated 2024-12-06
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant5.0 GB
Quick answer

Ninja V3 needs about 7.5 GB of memory at Q6_K (a 5.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 5.0 GB (Q5_K_S) to 14.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Ninja V3 is a 7.24B-parameter Ninja model in GGUF format, quantized by MaziyarPanahi. Its trained context length is 32K tokens. The repository has 5 quant files, from 5.0 GB (Q5_K_S) to 14.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S5.0 GB 6.6 GB
Fits Get file →
Q5_K_M5.1 GB 6.7 GB
Fits Get file →
Q6_K5.9 GB 7.5 GB
Tight Get file →
Q8_07.7 GB 9.3 GB
Too big Get file →
—14.5 GB 16.1 GB
Too big Get file →

What GPU do you need for Ninja 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: the best quant that fits is Q6_K (5.9 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (14.5 GB file, about 16.1 GB in use).

Which Ninja V3 quant should you choose?

Q6_K (5.9 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.

If memory is tight, the smallest file is Q5_K_S at 5.0 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMaziyarPanahi
FamilyNinja
Downloads (HF)195
Last updated2024-12-06

Frequently asked questions about Ninja V3

How much VRAM does Ninja V3 need?

About 7.5 GB at Q6_K with an 8K context window. That is the 5.9 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 Ninja V3 on an 8 GB GPU?

Yes, with Q6_K: the 5.9 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ninja V3 GGUF?

It depends on the quant: Q5_K_S is 5.0 GB, Q5_K_M is 5.1 GB, Q6_K is 5.9 GB, Q8_0 is 7.7 GB, file is 14.5 GB.

What context length does Ninja V3 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Ninja V3 GGUF?

The files are on Hugging Face in the MaziyarPanahi/Ninja-V3-nsfw-enhance-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Ninja-V3-nsfw-enhance

Similar models

Browse all →

More from MaziyarPanahi

All by MaziyarPanahi →

More Ninja models

All Ninja →

Other small models

All small models →