Hausa News Classifier needs about 1.0 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.2 GB (Q2_K) to 0.6 GB (F16).
Hausa news topic classifier based on BERT
The Hausa News Classifier predicts one of seven topics: business, entertainment, health, politics, religion, sports, technology. It is fine‑tuned from AfroXLMR‑base on the Hausa portion of MasakhaNEWS. Accuracy on the official test split is 0.9058.
Good at
- Classifying Hausa news into 7 topics
- Fast inference with small GGUF files
- Suitable for educational demos
Limits
- No vision support
- Limited to 7 topics, no "none of these" class
- Small training set may reduce generalisation
Best for
- Academic research on Hausa NLP
- Rapid prototyping of Hausa news classifiers
- Educational demonstrations of BERT fine‑tuning
Who it’s for. Researchers and developers working with Hausa language data who need a lightweight topic classifier. The model is ideal for educational settings and quick prototyping, but users should verify license terms before deployment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_S | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| IQ4_XS | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q3_K_L | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_S | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q5_K_M | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q6_K | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.8 GB | Fits | Get file → | |
| F16 | 0.6 GB | 1.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.22 GB) or Q5_K_M (0.23 GB). If memory is tighter, Q2_K (0.20 GB) or Q3_K_S (0.20 GB) provide the smallest files. All quants require roughly 1 GB of VRAM at 8 k context.
What GPU do you need for Hausa News Classifier?
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 (0.6 GB file, about 1.4 GB in use).
Which Hausa News Classifier quant should you choose?
Q4_K_M is the usual starting point for Hausa News Classifier: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.3 GB, about 1.4 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 0.2 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
Source
Frequently asked questions about Hausa News Classifier
How much VRAM does Hausa News Classifier need?
About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.2 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 Hausa News Classifier on an 8 GB GPU?
Yes, with F16: the 0.6 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Hausa News Classifier GGUF?
It depends on the quant: Q2_K is 0.2 GB, Q3_K_S is 0.2 GB, Q3_K_M is 0.2 GB, IQ4_XS is 0.2 GB, Q3_K_L is 0.2 GB, Q4_K_S is 0.2 GB and 6 more.
What context length does Hausa News Classifier 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 Hausa News Classifier GGUF?
The files are on Hugging Face in the mradermacher/hausa-news-classifier-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 this model on 8 GB VRAM?
Yes, the smallest quants (Q2_K, Q3_K_S) are 0.20 GB and need about 1 GB of VRAM at 8 k context.
Does this model support vision tasks?
No, it is a text‑only BERT classifier with no vision capabilities.
What topics can it predict?
It predicts business, entertainment, health, politics, religion, sports, and technology.