basal 1.5 4.5B needs about 3.9 GB of memory at Q4_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.9 GB (Q4_K_M) to 5.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.0 GB.
Basal 1.5 4.5B – a typed‑decision LLM for Polish and English
Basal 1.5 4.5B is a 4.76 B parameter llama‑style model that answers typed questions by returning calibrated probabilities for each option. It reads a state and outputs a single probability vector without generating text. The model is optimized for fast, accurate decision making.
Good at
- Fast typed‑decision classification
- Calibrated probability outputs
- Multi‑language (Polish, English)
Limits
- No text generation
- No vision support
- Requires 8 k context for estimates
Best for
- Routing with dynamic categories
- RAG relevance decisions
- Agent tool selection
Who it’s for. Developers building decision engines that need quick, reliable probability estimates for a set of options. The model is ideal for systems that require confidence thresholds without generating full responses.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.9 GB | 3.9 GB | Fits | Get file → | |
| Q8_0 | 5.1 GB | 6.1 GB | Fits | Get file → |
For 8 GB VRAM use the Q4_K_M file (2.93 GB, ~3.9 GB memory at 8 k context). For 12 GB VRAM or higher use Q8_0 (5.06 GB, ~6.1 GB memory at 8 k context). Estimates are approximate.
What GPU do you need for basal 1.5 4.5B?
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 Q4_K_M (2.9 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (2.9 GB file, about 3.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.1 GB file, about 6.1 GB in use).
Which basal 1.5 4.5B quant should you choose?
Q4_K_M is the usual starting point for basal 1.5 4.5B: it balances file size and quality well. Here it is a 2.9 GB file.
The Q8_0 file is 5.1 GB, about 1.7 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 basal 1.5 4.5B
How much VRAM does basal 1.5 4.5B need?
About 3.9 GB at Q4_K_M with an 8K context window. That is the 2.9 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 basal 1.5 4.5B on an 8 GB GPU?
Yes, with Q8_0: the 5.1 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of basal 1.5 4.5B GGUF?
It depends on the quant: Q4_K_M is 2.9 GB, Q8_0 is 5.1 GB.
What context length does basal 1.5 4.5B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.0 GB at 32K.
Where can I download basal 1.5 4.5B GGUF?
The files are on Hugging Face in the Remek/basal-1.5-4.5B-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 basal 1.5 4.5B 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 basal 1.5 4.5B on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 3.9 GB of VRAM at 8 k context, which fits in 8 GB.
Does the model support vision or text generation?
No, it is a typed‑decision model that returns probabilities and does not generate text or process images.
What license applies to this model?
The model is released under the Apache‑2.0 license.