BI

Bielik 4.5B v3.0 Instruct

BielikGGUF by second-stateUpdated 2025-05-07
Download on Hugging Face
Parameters4.76B
Context8K
Layers60
Architecturellama
Smallest quant1.8 GB
Quick answer

Bielik 4.5B v3.0 Instruct 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 13 quants, from 1.8 GB (Q2_K) to 9.5 GB (F16).

Bielik 4.5B v3.0 Instruct – 4.76B parameter instruction model

Bielik 4.5B v3.0 Instruct is a 4.76B parameter llama architecture model trained on 8192 token context. It is released under the apache-2.0 license and supports instruction following. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • ChatML prompt support
  • Large context 8192 tokens

Limits

  • No vision support
  • Requires 8k context for estimates
  • No mixture of experts

Best for

  • Chatbot development
  • Instruction-based applications
  • Contextual dialogue systems

Who it’s for. Developers building instruction‑driven chat applications who need a medium‑size llama model with flexible quantization options. The model is suitable for users with moderate GPU memory and a need for 8k token context.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.8 GB 2.8 GB
Fits Get file →
Q3_K_S2.1 GB 3.1 GB
Fits Get file →
Q3_K_M2.3 GB 3.3 GB
Fits Get file →
Q3_K_L2.5 GB 3.5 GB
Fits Get file →
Q4_02.7 GB 3.7 GB
Fits Get file →
Q4_K_S2.7 GB 3.7 GB
Fits Get file →
Q4_K_M2.9 GB 3.9 GB
Fits Get file →
Q5_03.3 GB 4.3 GB
Fits Get file →
Q5_K_S3.3 GB 4.3 GB
Fits Get file →
Q5_K_M3.4 GB 4.4 GB
Fits Get file →
Q6_K3.9 GB 4.9 GB
Fits Get file →
Q8_05.1 GB 6.1 GB
Fits Get file →
F169.5 GB 10.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (est. 3.9 GB) or Q4_0 (est. 3.7 GB). For 12 GB VRAM, Q5_K_M (est. 4.4 GB) or Q6_K (est. 4.9 GB) are suitable. Larger models like Q8_0 or F16 require more than 10 GB VRAM.

What GPU do you need for Bielik 4.5B v3.0 Instruct?

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 Q6_K (3.9 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.1 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (9.5 GB file, about 10.5 GB in use).

Which Bielik 4.5B v3.0 Instruct quant should you choose?

Q4_K_M is the usual starting point for Bielik 4.5B v3.0 Instruct: it balances file size and quality well. Here it is a 2.9 GB file.

The Q8_0 file is 5.1 GB, about 1.8 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 Q2_K at 1.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters4.76B
Layers60
Trained context8,192 tokens
KV cache (fp16)60 KB per token

Source

Quantized bysecond-state
FamilyBielik
Licenseapache-2.0
Downloads (HF)1,108
Last updated2025-05-07

Frequently asked questions about Bielik 4.5B v3.0 Instruct

How much VRAM does Bielik 4.5B v3.0 Instruct 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 v3.0 Instruct 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 Bielik 4.5B v3.0 Instruct GGUF?

It depends on the quant: Q2_K is 1.8 GB, Q3_K_S is 2.1 GB, Q3_K_M is 2.3 GB, Q3_K_L is 2.5 GB, Q4_0 is 2.7 GB, Q4_K_S is 2.7 GB and 7 more.

What context length does Bielik 4.5B v3.0 Instruct support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.5 GB at 8K.

Where can I download Bielik 4.5B v3.0 Instruct GGUF?

The files are on Hugging Face in the second-state/Bielik-4.5B-v3.0-Instruct-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 v3.0 Instruct 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 Q4_K_M on 8 GB VRAM?

Yes, Q4_K_M estimates 3.9 GB memory at 8k context, fitting within 8 GB VRAM.

What context size does this model support?

The model supports a context size of 8192 tokens.

Is this model licensed for commercial use?

It is released under the apache-2.0 license, which allows commercial use.

Other GGUFs of Bielik-4.5B-v3.0-Instruct

Similar models

Browse all →

More from second-state

All by second-state →

More Bielik models

All Bielik →

Other small models

All small models →