GLiNER2.5-Decide needs about 1.6 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.3 GB (Q4_K_M) to 0.9 GB (F16).
GLiNER2.5-Decide: a decision model for llama.cpp
GLiNER2.5-Decide is a zero‑shot classifier that scores a set of labels in a single forward pass. It uses a 2‑layer MLP decision head inside the GGUF. The model is built on DeBERTa‑v3 with 0.436B parameters.
Good at
- Zero‑shot classification
- Single‑pass label scoring
- Decision head integration
Limits
- Requires llama.cpp with decision port
- Context size fixed at 512 tokens
- No per‑token head or embedding endpoint
Best for
- Label‑set scoring in chatbots
- Fast inference on small GPUs
- Embedded decision tasks
Who it’s for. Developers needing a lightweight decision model for llama.cpp. It is suitable for applications that require quick label scoring without a separate embedding service.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.5 GB | 1.0 GB | Fits | Get file → | |
| F16 | 0.9 GB | 1.4 GB | Fits | Get file → |
For 8 GB VRAM, use Q8_0 (0.47 GB file, 1.8 GB memory at 8k context). For tighter budgets, Q4_K_M (0.30 GB file, 1.6 GB memory) is available. F16 is larger and not recommended for limited memory.
What GPU do you need for GLiNER2.5-Decide?
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 (0.9 GB file, about 2.2 GB in use).
Which GLiNER2.5-Decide quant should you choose?
Q4_K_M is the usual starting point for GLiNER2.5-Decide: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.5 GB, about 1.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLiNER2.5-Decide
How much VRAM does GLiNER2.5-Decide need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.3 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 GLiNER2.5-Decide on an 8 GB GPU?
Yes, with F16: the 0.9 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GLiNER2.5-Decide GGUF?
It depends on the quant: Q4_K_M is 0.3 GB, Q8_0 is 0.5 GB, F16 is 0.9 GB.
What context length does GLiNER2.5-Decide support?
The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.1 GB at 512.
Where can I download GLiNER2.5-Decide GGUF?
The files are on Hugging Face in the 3ntr0py-t4m3r/GLiNER2.5-Decide-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does GLiNER2.5-Decide 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.
Can I run GLiNER2.5-Decide on an 8 GB VRAM card?
Yes, use the Q8_0 quantization which requires about 1.8 GB of VRAM at 8k context.
Does the model support vision or audio?
No, the model is purely text‑based and has no vision or audio capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.