TE

tensor bank

TensorGGUF by gguf-orgUpdated 2026-08-31
Download on Hugging Face
Parameters—
Context—
Layers—
Architecturepig
Smallest quant0.0 GB
Quick answer

tensor bank needs about 0.5 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 49 quants, from 0.0 GB (F16) to 0.1 GB (MXFP4_MOE).

Tensor Bank – a sandbox model for tensor transfer

Tensor Bank is a lightweight model from the Tensor family with no defined parameter count. It is released under the MIT license and supports multiple quantization formats. The model is designed for experimentation with tensor transfer protocols.

Good at

  • Flexible quantization support
  • Low memory footprint
  • MIT licensed

Limits

  • No defined context length
  • No vision or multimodal capabilities
  • No training data disclosed

Best for

  • Testing new quantization pipelines
  • Learning tensor transfer concepts
  • Rapid prototyping on low‑memory devices

Who it’s for. Developers and researchers who want a minimal, MIT‑licensed model to experiment with tensor transfer protocols and quantization techniques. The model is suitable for educational purposes and quick prototyping.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.0 GB 0.5 GB
Fits Get file →
F320.0 GB 0.5 GB
Fits Get file →
F160.0 GB 0.5 GB
Fits Get file →
F320.0 GB 0.5 GB
Fits Get file →
Q8_10.0 GB 0.5 GB
Fits Get file →
Q2_00.0 GB 0.5 GB
Fits Get file →
TQ1_00.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
Q8_K0.0 GB 0.5 GB
Fits Get file →
TQ2_00.0 GB 0.5 GB
Fits Get file →
F160.0 GB 0.5 GB
Fits Get file →
Q2_K0.0 GB 0.5 GB
Fits Get file →
Q2_K_S0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
F160.0 GB 0.5 GB
Fits Get file →
IQ3_XXS0.0 GB 0.5 GB
Fits Get file →
IQ3_S0.0 GB 0.5 GB
Fits Get file →
Q3_K_L0.0 GB 0.5 GB
Fits Get file →
Q3_K_M0.0 GB 0.5 GB
Fits Get file →
Q3_K_S0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
IQ4_XS0.0 GB 0.5 GB
Fits Get file →
IQ4_NL0.0 GB 0.5 GB
Fits Get file →
Q4_00.0 GB 0.5 GB
Fits Get file →
Q4_K_M0.0 GB 0.5 GB
Fits Get file →
Q4_K_S0.0 GB 0.5 GB
Fits Get file →
F320.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
Q4_10.0 GB 0.5 GB
Fits Get file →
F320.0 GB 0.5 GB
Fits Get file →
Q5_00.0 GB 0.5 GB
Fits Get file →
Q5_K_M0.0 GB 0.5 GB
Fits Get file →
Q5_K_S0.0 GB 0.5 GB
Fits Get file →
Q5_10.0 GB 0.5 GB
Fits Get file →
IQ1_S0.0 GB 0.5 GB
Fits Get file →
Q6_K0.0 GB 0.5 GB
Fits Get file →
IQ1_M0.0 GB 0.5 GB
Fits Get file →
Q1_00.0 GB 0.5 GB
Fits Get file →
IQ2_XXS0.0 GB 0.5 GB
Fits Get file →
Q8_00.0 GB 0.5 GB
Fits Get file →
IQ2_XS0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
MXFP4_MOE0.0 GB 0.5 GB
Fits Get file →
BF160.0 GB 0.5 GB
Fits Get file →
F160.0 GB 0.5 GB
Fits Get file →
IQ2_S0.0 GB 0.5 GB
Fits Get file →
—0.0 GB 0.5 GB
Fits Get file →
F320.0 GB 0.5 GB
Fits Get file →
MXFP4_MOE0.1 GB 0.7 GB
Fits Get file →

For 8 GB VRAM, use any quant with estimated memory 0.5 GB, such as Q4_K_M or Q5_0. If you have 4 GB VRAM, choose a smaller quant like Q2_K_S. For the lowest memory usage, the MXFP4_MOE quant uses 0.7 GB at 8 k context and is suitable for very constrained setups.

What GPU do you need for tensor bank?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is MXFP4_MOE (0.1 GB file, about 0.7 GB in use).

Which tensor bank quant should you choose?

Q4_K_M is the usual starting point for tensor bank: it balances file size and quality well. Here it is a 0.0 GB file.

The Q8_0 file is 0.0 GB, about 1.9 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is F16 at 0.0 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturepig

Source

Quantized bygguf-org
FamilyTensor
Licensemit
Downloads (HF)4,461
Last updated2026-08-31

Frequently asked questions about tensor bank

How much VRAM does tensor bank need?

About 0.5 GB at Q4_K_M with an 8K context window. That is the 0.0 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 tensor bank on an 8 GB GPU?

Yes, with MXFP4_MOE: the 0.1 GB file needs about 0.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of tensor bank GGUF?

It depends on the quant: F16 is 0.0 GB, F32 is 0.0 GB, F16 is 0.0 GB, F32 is 0.0 GB, Q8_1 is 0.0 GB, Q2_0 is 0.0 GB and 43 more.

Where can I download tensor bank GGUF?

The files are on Hugging Face in the gguf-org/tensor-bank repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does tensor bank use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Tensor Bank on 4 GB VRAM?

Yes, any quant with an estimated memory of 0.5 GB will fit in 4 GB VRAM, such as Q2_K_S or Q4_K_S.

Does Tensor Bank support vision or multimodal input?

No, the model has no vision or multimodal capabilities.

More from gguf-org

All by gguf-org →