TA

Tankie NB 3B SFT v1

TankieGGUF by latinleninUpdated 2026-02-10
Download on Hugging Face
Parameters3.93B
Context64K
Layers32
Architecturellama
Smallest quant4.2 GB
Quick answer

Tankie NB 3B SFT v1 needs about 5.2 GB of memory at Q8_0 (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

Tankie NB 3B SFT v1 is a 3.93B-parameter Tankie model in GGUF format, quantized by latinlenin. Its trained context length is 64K tokens. The repository has 1 quant file, from 4.2 GB (Q8_0) to 4.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_04.2 GB 5.2 GB
Fits Get file →

What GPU do you need for Tankie NB 3B SFT v1?

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: the best quant that fits is Q8_0 (4.2 GB file, about 5.2 GB in use).

Which Tankie NB 3B SFT v1 quant should you choose?

Q8_0 (4.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.93B
Layers32
Trained context65,536 tokens
KV cache (fp16)64 KB per token

Source

Quantized bylatinlenin
FamilyTankie
Licenseapache-2.0
Downloads (HF)2
Last updated2026-02-10

Frequently asked questions about Tankie NB 3B SFT v1

How much VRAM does Tankie NB 3B SFT v1 need?

About 5.2 GB at Q8_0 with an 8K context window. That is the 4.2 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 Tankie NB 3B SFT v1 on an 8 GB GPU?

Yes, with Q8_0: the 4.2 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Tankie NB 3B SFT v1 GGUF?

It depends on the quant: Q8_0 is 4.2 GB.

What context length does Tankie NB 3B SFT v1 support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download Tankie NB 3B SFT v1 GGUF?

The files are on Hugging Face in the latinlenin/Tankie-NB-3B-SFT-v1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Tankie NB 3B SFT v1 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 latinlenin

All by latinlenin →

More Tankie models

All Tankie →

Other small models

All small models →