bielik 1.5b v3 matura history sft2 needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 0.0 GB to 3.2 GB (BF16).
Bielik‑1.5B‑v3: Polish history matura SFT model
Bielik‑1.5B‑v3 is a 1.6‑billion‑parameter Llama‑style model fine‑tuned on Polish extended‑level history matura tasks. It is optimized for the "Mały, ale wariat" track of the SlayerLab hackathon and achieves at least 35 % on the team evaluator. The model is released under Apache‑2.0.
Good at
- Polish history matura tasks
- SFT on synthetic essays
- Closed‑answer retrieval
Limits
- No vision support
- Requires 8 k context
- Only available in GGUF format
Best for
- Academic tutoring in Polish history
- Generating exam‑style essays
- Evaluating model performance on matura tasks
Who it’s for. Students and educators seeking a lightweight Polish history model for exam preparation. Researchers testing SFT on specialized curricula may also find it useful.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.8 GB | Fits | Get file → | |
| IQ3_XXS | 0.6 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_S | 0.7 GB | 1.5 GB | Fits | Get file → | |
| IQ3_M | 0.7 GB | 1.5 GB | Fits | Get file → | |
| — | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_M | 0.8 GB | 1.6 GB | Fits | Get file → | |
| IQ4_XS | 0.9 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 1.0 GB | 1.7 GB | Fits | Get file → | |
| Q8_0 | 1.7 GB | 2.5 GB | Fits | Get file → | |
| BF16 | 3.2 GB | 4.0 GB | Fits | Get file → |
For 8 GB VRAM, use IQ4_XS (0.87 GB, 1.6 GB memory) or Q4_K_M (0.97 GB, 1.7 GB memory). If 4 GB VRAM is available, IQ3_XXS (0.63 GB, 1.4 GB memory) is suitable. Larger models such as Q8_0 or BF16 require more memory and are not recommended for low‑budget setups.
What GPU do you need for bielik 1.5b v3 matura history sft2?
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 BF16 (3.2 GB file, about 4.0 GB in use).
Which bielik 1.5b v3 matura history sft2 quant should you choose?
Q4_K_M is the usual starting point for bielik 1.5b v3 matura history sft2: it balances file size and quality well. Here it is a 1.0 GB file.
The Q8_0 file is 1.7 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.
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 1.5b v3 matura history sft2
How much VRAM does bielik 1.5b v3 matura history sft2 need?
About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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 1.5b v3 matura history sft2 on an 8 GB GPU?
Yes, with BF16: the 3.2 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of bielik 1.5b v3 matura history sft2 GGUF?
It depends on the quant: file is 0.0 GB, IQ3_XXS is 0.6 GB, Q3_K_S is 0.7 GB, IQ3_M is 0.7 GB, file is 0.8 GB, Q3_K_M is 0.8 GB and 4 more.
What context length does bielik 1.5b v3 matura history sft2 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.3 GB at 8K.
Where can I download bielik 1.5b v3 matura history sft2 GGUF?
The files are on Hugging Face in the SlayerLab/bielik-1.5b-v3-matura-history-sft2 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 1.5b v3 matura history sft2 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 IQ4_XS quant uses about 1.6 GB of VRAM at 8 k context, which fits within an 8 GB GPU.
Does this model support vision tasks?
No, the model is purely text‑based and has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.