UN

UNSPSC Roberta

UnspscGGUF by mradermacherUpdated 2025-08-09
Download on Hugging Face
Parameters125M
Context512
Layers12
Architecturebert
Smallest quant0.1 GB
Quick answer

UNSPSC Roberta needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.1 GB (Q2_K) to 0.3 GB (F16).

UNSPSC Roberta – 125M‑parameter BERT model in GGUF format

UNSPSC Roberta is a 0.125‑billion‑parameter BERT model quantized for efficient inference. It supports a 512‑token context and is available in multiple static quantizations. The model is hosted on the Hugging Face repository mradermacher/UNSPSC-roberta-GGUF.

Good at

  • Text classification
  • Named entity recognition
  • Sentiment analysis

Limits

  • 512‑token context only
  • No vision capabilities
  • License not specified

Best for

  • Small‑scale NLP tasks
  • Edge inference
  • Educational demos

Who it’s for. Developers needing a lightweight BERT variant for local inference. Researchers exploring quantization effects on BERT models. Educators teaching NLP on limited hardware.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.1 GB 0.6 GB
Fits Get file →
Q3_K_S0.1 GB 0.6 GB
Fits Get file →
Q3_K_M0.1 GB 0.6 GB
Fits Get file →
IQ4_XS0.1 GB 0.6 GB
Fits Get file →
Q3_K_L0.1 GB 0.6 GB
Fits Get file →
Q4_K_S0.1 GB 0.6 GB
Fits Get file →
Q4_K_M0.1 GB 0.6 GB
Fits Get file →
Q5_K_S0.1 GB 0.6 GB
Fits Get file →
Q5_K_M0.1 GB 0.6 GB
Fits Get file →
Q6_K0.1 GB 0.6 GB
Fits Get file →
Q8_00.1 GB 0.7 GB
Fits Get file →
F160.3 GB 0.8 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.09 GB file, ~0.9 GB memory). If 4 GB VRAM is available, Q2_K or Q3_K_S (0.07 GB file) are suitable. For higher precision, Q8_0 (0.14 GB file) requires ~0.9 GB memory.

What GPU do you need for UNSPSC Roberta?

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: the best quant that fits is F16 (0.3 GB file, about 1.1 GB in use).

Which UNSPSC Roberta quant should you choose?

Q4_K_M is the usual starting point for UNSPSC Roberta: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.1 GB, about 1.5 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 Q2_K at 0.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebert
Parameters125M
Layers12
Trained context512 tokens
KV cache (fp16)36 KB per token

Source

Quantized bymradermacher
FamilyUnspsc
Downloads (HF)799
Last updated2025-08-09

Frequently asked questions about UNSPSC Roberta

How much VRAM does UNSPSC Roberta need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.1 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 UNSPSC Roberta on an 8 GB GPU?

Yes, with F16: the 0.3 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of UNSPSC Roberta GGUF?

It depends on the quant: Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, Q3_K_M is 0.1 GB, IQ4_XS is 0.1 GB, Q3_K_L is 0.1 GB, Q4_K_S is 0.1 GB and 6 more.

What context length does UNSPSC Roberta support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.0 GB at 512.

Where can I download UNSPSC Roberta GGUF?

The files are on Hugging Face in the mradermacher/UNSPSC-roberta-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run UNSPSC Roberta on 8 GB VRAM?

Yes, Q4_K_M or Q4_K_S quantizations fit within 8 GB VRAM, using about 0.9 GB memory at 8k context.

Does the model support vision tasks?

No, UNSPSC Roberta is a text‑only BERT model with no vision capabilities.

What is the maximum context length?

The model supports a maximum context of 512 tokens.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other tiny models

All tiny models →