BI

Bielik Minitron 7B v3.0 Instruct Heretic

BielikGGUF by mradermacherUpdated 2026-07-09
Download on Hugging Face
Parameters7.48B
Context32K
Layers40
Architecturellama
Smallest quant0.0 GB
Quick answer

Bielik Minitron 7B v3.0 Instruct Heretic needs about 6.3 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 6.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Bielik Minitron 7B v3.0 Instruct Heretic – 7.48B parameter text model

Bielik Minitron 7B v3.0 Instruct Heretic is a 7.48B parameter generative text model based on the llama architecture. It supports a 32768 token context window and is released under the apache-2.0 license. The model is optimized for European languages, particularly Polish.

Good at

  • Large context handling
  • Multilingual text generation
  • Instruction following

Limits

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

Best for

  • Chatbot development
  • Content creation
  • Code generation

Who it’s for. Developers and researchers needing a compact, instruction‑aligned model for European languages. The model is suitable for local deployment with llama.cpp and GGUF files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.8 GB
Fits Get file →
IQ1_S1.7 GB 3.5 GB
Fits Get file →
IQ1_M1.8 GB 3.7 GB
Fits Get file →
IQ2_XXS2.1 GB 3.9 GB
Fits Get file →
IQ2_XS2.3 GB 4.1 GB
Fits Get file →
IQ2_S2.4 GB 4.2 GB
Fits Get file →
IQ2_M2.6 GB 4.4 GB
Fits Get file →
Q2_K_S2.6 GB 4.5 GB
Fits Get file →
Q2_K2.8 GB 4.7 GB
Fits Get file →
IQ3_XXS2.9 GB 4.8 GB
Fits Get file →
IQ3_XS3.1 GB 5.0 GB
Fits Get file →
Q3_K_S3.3 GB 5.1 GB
Fits Get file →
IQ3_S3.3 GB 5.1 GB
Fits Get file →
IQ3_M3.4 GB 5.3 GB
Fits Get file →
Q3_K_M3.6 GB 5.5 GB
Fits Get file →
Q3_K_L4.0 GB 5.8 GB
Fits Get file →
IQ4_XS4.0 GB 5.9 GB
Fits Get file →
Q4_04.3 GB 6.1 GB
Fits Get file →
IQ4_NL4.3 GB 6.1 GB
Fits Get file →
Q4_K_S4.3 GB 6.1 GB
Fits Get file →
Q4_K_M4.5 GB 6.3 GB
Fits Get file →
Q4_14.7 GB 6.5 GB
Fits Get file →
Q5_K_S5.2 GB 7.0 GB
Fits Get file →
Q5_K_M5.3 GB 7.1 GB
Fits Get file →
Q6_K6.1 GB 8.0 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M (file size 4.5 GB, memory 6.3 GB). For 12 GB VRAM, Q5_K_M (file size 5.29 GB, memory 7.1 GB). For 16 GB VRAM, Q6_K (file size 6.14 GB, memory 8 GB).

What GPU do you need for Bielik Minitron 7B v3.0 Instruct 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 IQ2_XXS (2.1 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.0 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.1 GB file, about 8.0 GB in use).

Which Bielik Minitron 7B v3.0 Instruct Heretic quant should you choose?

Q4_K_M is the usual starting point for Bielik Minitron 7B v3.0 Instruct Heretic: it balances file size and quality well. Here it is a 4.5 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

Architecturellama
Parameters7.48B
Layers40
Trained context32,768 tokens
KV cache (fp16)160 KB per token

Frequently asked questions about Bielik Minitron 7B v3.0 Instruct Heretic

How much VRAM does Bielik Minitron 7B v3.0 Instruct Heretic need?

About 6.3 GB at Q4_K_M with an 8K context window. That is the 4.5 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 Minitron 7B v3.0 Instruct Heretic on an 8 GB GPU?

Yes, with Q6_K: the 6.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bielik Minitron 7B v3.0 Instruct Heretic GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 1.7 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.1 GB, IQ2_XS is 2.3 GB, IQ2_S is 2.4 GB and 19 more.

What context length does Bielik Minitron 7B v3.0 Instruct 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 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Bielik Minitron 7B v3.0 Instruct Heretic GGUF?

The files are on Hugging Face in the mradermacher/Bielik-Minitron-7B-v3.0-Instruct-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 Minitron 7B v3.0 Instruct 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, using the Q4_K_M quant which estimates 6.3 GB memory at 8k context.

Does this model support vision tasks?

No, it is a text‑only model.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Bielik-Minitron-7B-v3.0-Instruct-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Bielik models

All Bielik →

Other small models

All small models →