RA

Racka 4B

RackaGGUF by elte-nlpUpdated 2026-07-15
Download on Hugging Face
Parameters4.02B
Context40K
Layers—
Architectureqwen3
Smallest quant1.9 GB
Quick answer

Racka 4B needs about 3.3 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 1.9 GB (IQ3_S) to 8.1 GB (BF16).

Racka 4B is a 4.02B-parameter Racka model in GGUF format, quantized by elte-nlp. Its trained context length is 40K tokens. The repository has 6 quant files, from 1.9 GB (IQ3_S) to 8.1 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_S1.9 GB 2.6 GB
Fits Get file →
Q4_K_M2.5 GB 3.3 GB
Fits Get file →
Q4_K_M2.5 GB 3.3 GB
Fits Get file →
Q5_K_M2.9 GB 3.7 GB
Fits Get file →
Q8_04.3 GB 5.3 GB
Fits Get file →
BF168.1 GB 9.5 GB
Too big Get file →

What GPU do you need for Racka 4B?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q5_K_M (2.9 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.3 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.5 GB in use).

Which Racka 4B quant should you choose?

Q4_K_M is the usual starting point for Racka 4B: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.3 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 IQ3_S at 1.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4.02B
Trained context40,960 tokens

Source

Quantized byelte-nlp
FamilyRacka
Downloads (HF)147
Last updated2026-07-15

Frequently asked questions about Racka 4B

How much VRAM does Racka 4B need?

About 3.3 GB at Q4_K_M with an 8K context window. That is the 2.5 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 Racka 4B on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Racka 4B GGUF?

It depends on the quant: IQ3_S is 1.9 GB, Q4_K_M is 2.5 GB, Q4_K_M is 2.5 GB, Q5_K_M is 2.9 GB, Q8_0 is 4.3 GB, BF16 is 8.1 GB.

What context length does Racka 4B support?

The GGUF header lists a trained context length of 40,960 tokens (40K).

Where can I download Racka 4B GGUF?

The files are on Hugging Face in the elte-nlp/Racka-4B-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 Racka 4B use?

Hugging Face lists the license as cc-by-nc-sa-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Racka-4B

Similar models

Browse all →

More Racka models

All Racka →

Other small models

All small models →