Bielik 4.5B v3 Heretic 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 25 quants, from 0.0 GB to 3.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.0 GB.
Bielik 4.5B v3 Heretic – a 4.76B parameter Polish text model
Bielik 4.5B v3 Heretic is a 4.76 billion parameter llama architecture model trained on Polish corpora. It supports a 32768 token context window and is released under the apache-2.0 license.
Good at
- Polish language understanding
- Large context handling
- Fine‑tuning ready
Limits
- No vision support
- Requires 8k context for memory estimates
- No active parameters specified
Best for
- Polish text generation
- Fine‑tuning Polish datasets
- Research on large context models
Who it’s for. Developers and researchers needing a Polish language model with a large context window. The model is a base for further fine‑tuning and is not pre‑trained for instruction following.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ1_S | 1.0 GB | 2.0 GB | Fits | Get file → | |
| IQ1_M | 1.1 GB | 2.1 GB | Fits | Get file → | |
| IQ2_XXS | 1.3 GB | 2.3 GB | Fits | Get file → | |
| IQ2_XS | 1.4 GB | 2.4 GB | Fits | Get file → | |
| IQ2_S | 1.5 GB | 2.5 GB | Fits | Get file → | |
| IQ2_M | 1.6 GB | 2.6 GB | Fits | Get file → | |
| Q2_K_S | 1.6 GB | 2.6 GB | Fits | Get file → | |
| Q2_K | 1.8 GB | 2.8 GB | Fits | Get file → | |
| IQ3_XXS | 1.9 GB | 2.9 GB | Fits | Get file → | |
| IQ3_XS | 2.0 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.1 GB | Fits | Get file → | |
| IQ3_S | 2.1 GB | 3.1 GB | Fits | Get file → | |
| IQ3_M | 2.1 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_M | 2.3 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_L | 2.5 GB | 3.5 GB | Fits | Get file → | |
| IQ4_XS | 2.6 GB | 3.6 GB | Fits | Get file → | |
| IQ4_NL | 2.7 GB | 3.7 GB | Fits | Get file → | |
| Q4_0 | 2.7 GB | 3.7 GB | Fits | Get file → | |
| Q4_K_S | 2.7 GB | 3.7 GB | Fits | Get file → | |
| Q4_K_M | 2.9 GB | 3.9 GB | Fits | Get file → | |
| Q4_1 | 3.0 GB | 4.0 GB | Fits | Get file → | |
| Q5_K_S | 3.3 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_M | 3.4 GB | 4.4 GB | Fits | Get file → | |
| Q6_K | 3.9 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (2.88 GB file, 3.9 GB memory at 8k context). For 6 GB VRAM, use Q3_K_M (2.3 GB file, 3.3 GB memory). For 4 GB VRAM, use IQ2_XS (1.43 GB file, 2.4 GB memory).
What GPU do you need for Bielik 4.5B v3 Heretic?
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_1 (3.0 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.9 GB file, about 4.9 GB in use).
Which Bielik 4.5B v3 Heretic quant should you choose?
Q4_K_M is the usual starting point for Bielik 4.5B v3 Heretic: it balances file size and quality well. Here it is a 2.9 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Bielik 4.5B v3 Heretic
How much VRAM does Bielik 4.5B v3 Heretic 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 Bielik 4.5B v3 Heretic on an 8 GB GPU?
Yes, with Q6_K: the 3.9 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Bielik 4.5B v3 Heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.0 GB, IQ1_M is 1.1 GB, IQ2_XXS is 1.3 GB, IQ2_XS is 1.4 GB, IQ2_S is 1.5 GB and 19 more.
What context length does Bielik 4.5B v3 Heretic 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 Bielik 4.5B v3 Heretic GGUF?
The files are on Hugging Face in the mradermacher/Bielik-4.5B-v3-heretic-i1-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 Bielik 4.5B v3 Heretic 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant uses 3.9 GB memory at 8k context, which fits within 8 GB VRAM.
Does this model support vision tasks?
No, the model has no vision support.
What license does it use?
The model is released under the apache-2.0 license.