Basal 2.0 4.5B needs about 4.4 GB of memory at Q5_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 4 quants, from 3.4 GB (Q5_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 2.0 4.5B – a 4.5B parameter Llama model
Basal 2.0 4.5B is a 4.76B parameter Llama model derived from Bielik‑4.5B‑v3.0‑Instruct. It supports a 32,768 token context window and is released under the Apache‑2.0 license.
Good at
- Large context handling
- Decision‑layer prompt generation
- Typed‑decision API
Limits
- No vision support
- Requires a separate server for full typed‑decision output
- Limited to 4,096 tokens in Ollama mode
Best for
- Chatbots needing long context
- Decision‑based applications
- LLM inference on local hardware
Who it’s for. Developers and researchers who need a Llama‑based model with a large context window and typed‑decision capabilities. The model is suitable for local deployment via Ollama or llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 3.4 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 3.4 GB | 4.4 GB | Fits | Get file → | |
| Q8_0 | 5.1 GB | 6.1 GB | Fits | Get file → | |
| Q8_0 | 5.1 GB | 6.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q5_K_M (file size 3.42 GB, estimated 4.4 GB memory at 8 k context). For 12 GB VRAM, Q8_0 (file size 5.06 GB, estimated 6.1 GB memory) provides higher precision.
What GPU do you need for Basal 2.0 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q5_K_M (3.4 GB file, about 4.4 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 2.0 4.5B quant should you choose?
Q5_K_M (3.4 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q5_K_M at 3.4 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Basal 2.0 4.5B
How much VRAM does Basal 2.0 4.5B need?
About 4.4 GB at Q5_K_M with an 8K context window. That is the 3.4 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 2.0 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 2.0 4.5B GGUF?
It depends on the quant: Q5_K_M is 3.4 GB, Q5_K_M is 3.4 GB, Q8_0 is 5.1 GB, Q8_0 is 5.1 GB.
What context length does Basal 2.0 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 2.0 4.5B GGUF?
The files are on Hugging Face in the Remek/basal-2.0-4.5B-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 2.0 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 2.0 4.5B on 8 GB VRAM?
Yes, using the Q5_K_M quantization which requires about 4.4 GB of VRAM at 8 k context.
Does the model support vision?
No, Basal 2.0 4.5B has no vision capabilities.
What is the maximum context length?
The model supports up to 32,768 tokens in context.