NI

NightWing3 Virtuoso 10B v0.2 IQ4 NL

NightwingGGUF by Nitrals-QuantsUpdated 2025-02-03
Download on Hugging Face
Parameters10.3B
Context32K
Layers40
Architecturellama
Smallest quant5.9 GB
Quick answer

NightWing3 Virtuoso 10B v0.2 IQ4 NL needs about 7.7 GB of memory at IQ4_NL (a 5.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

NightWing3 Virtuoso 10B v0.2 IQ4 NL is a 10.3B-parameter Nightwing model in GGUF format, quantized by Nitrals-Quants. Its trained context length is 32K tokens. The repository has 1 quant file, from 5.9 GB (IQ4_NL) to 5.9 GB (IQ4_NL).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL5.9 GB 7.7 GB
Tight Get file →

What GPU do you need for NightWing3 Virtuoso 10B v0.2 IQ4 NL?

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 IQ4_NL (5.9 GB file, about 7.7 GB in use).

Which NightWing3 Virtuoso 10B v0.2 IQ4 NL quant should you choose?

IQ4_NL (5.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.3B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Source

Quantized byNitrals-Quants
FamilyNightwing
Downloads (HF)4
Last updated2025-02-03

Frequently asked questions about NightWing3 Virtuoso 10B v0.2 IQ4 NL

How much VRAM does NightWing3 Virtuoso 10B v0.2 IQ4 NL need?

About 7.7 GB at IQ4_NL 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 NightWing3 Virtuoso 10B v0.2 IQ4 NL on an 8 GB GPU?

Yes, with IQ4_NL: the 5.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NightWing3 Virtuoso 10B v0.2 IQ4 NL GGUF?

It depends on the quant: IQ4_NL is 5.9 GB.

What context length does NightWing3 Virtuoso 10B v0.2 IQ4 NL support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download NightWing3 Virtuoso 10B v0.2 IQ4 NL GGUF?

The files are on Hugging Face in the Nitrals-Quants/NightWing3_Virtuoso-10B-v0.2-IQ4_NL-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 NightWing3_Virtuoso-10B-v0.2

Similar models

Browse all →

More from Nitrals-Quants

All by Nitrals-Quants →

More Nightwing models

All Nightwing →

Other medium models

All medium models →