BI

Bielik 11B v2.3 Instruct

BielikGGUF by speakleashUpdated 2024-11-26
Download on Hugging Face
Parameters11.2B
Context32K
Layers50
Architecturellama
Smallest quant6.7 GB
Quick answer

Bielik 11B v2.3 Instruct needs about 8.9 GB of memory at Q4_K_M (a 6.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 6.7 GB (Q4_K_M) to 12.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.

Bielik 11B v2.3 Instruct – Polish‑focused generative text model

Bielik 11B v2.3 Instruct is a 11.2 billion‑parameter causal decoder‑only model fine‑tuned on Polish text. It is a linear merge of earlier Bielik‑11B‑v2.x Instruct versions and was trained on over 20 million instructions and 10 billion tokens. The model is released under Apache 2.0.

Good at

  • Polish language understanding
  • Instruction following
  • Text generation

Limits

  • No vision support
  • Large VRAM requirement for higher quantisations
  • Requires 8 k context for memory estimates

Best for

  • Polish content creation
  • Chatbot development in Polish
  • Academic research on Polish NLP

Who it’s for. Developers and researchers needing a Polish‑centric LLM for local deployment. The model is suitable for users with GPU resources capable of handling 8 k context and the chosen quantisation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M6.7 GB 8.9 GB
Too big Get file →
Q5_K_M7.9 GB 10.1 GB
Too big Get file →
Q6_K9.2 GB 11.3 GB
Too big Get file →
Q8_011.9 GB 14.0 GB
Too big Get file →
Q8_012.1 GB 14.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (6.72 GB file, ~8.9 GB VRAM at 8 k context). For 12 GB VRAM, Q5_K_M (7.91 GB file, ~10.1 GB VRAM). Higher quantisations (Q6_K, Q8_0) need 14 GB+ VRAM and are not recommended for most users.

What GPU do you need for Bielik 11B v2.3 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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q6_K (9.2 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.1 GB file, about 14.3 GB in use).

Which Bielik 11B v2.3 Instruct quant should you choose?

Q4_K_M is the usual starting point for Bielik 11B v2.3 Instruct: it balances file size and quality well. Here it is a 6.7 GB file.

The Q8_0 file is 11.9 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters11.2B
Layers50
Trained context32,768 tokens
KV cache (fp16)200 KB per token

Source

Quantized byspeakleash
FamilyBielik
Licenseapache-2.0
Downloads (HF)2,366
Last updated2024-11-26

Frequently asked questions about Bielik 11B v2.3 Instruct

How much VRAM does Bielik 11B v2.3 Instruct need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 6.7 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 11B v2.3 Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Bielik 11B v2.3 Instruct GGUF?

It depends on the quant: Q4_K_M is 6.7 GB, Q5_K_M is 7.9 GB, Q6_K is 9.2 GB, Q8_0 is 11.9 GB, Q8_0 is 12.1 GB.

What context length does Bielik 11B v2.3 Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.

Where can I download Bielik 11B v2.3 Instruct GGUF?

The files are on Hugging Face in the speakleash/Bielik-11B-v2.3-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 11B v2.3 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 Bielik 11B v2.3 Instruct on 8 GB VRAM?

Yes, the Q4_K_M quantisation requires about 8.9 GB VRAM at 8 k context, which fits within an 8 GB GPU with some headroom.

Does the model support English?

The model is trained primarily on Polish text; English support is limited and may produce lower quality responses.

Is the model free to use?

Yes, it is released under the Apache 2.0 license, allowing free use and modification.

Other GGUFs of Bielik-11B-v2.3-Instruct

Similar models

Browse all →

More from speakleash

All by speakleash →

More Bielik models

All Bielik →

Other medium models

All medium models →