GR

Ektome granite 3.0 8b instruct PristinelyUncensored

GraniteGGUF by ZynerjiUpdated 2026-07-27
Download on Hugging Face
Parameters8.17B
Context4K
Layers40
Architecturegranite
Smallest quant3.7 GB
Quick answer

Ektome granite 3.0 8b instruct PristinelyUncensored needs about 6.8 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 3.7 GB (IQ3_M) to 8.7 GB (Q8_0).

Ektome granite 3.0 8b instruct PristinelyUncensored – 8.17B parameter uncensored instruction model

Ektome granite 3.0 8b instruct PristinelyUncensored is a 8.17B parameter model based on Granite‑3.0‑8B‑Instruct. It is uncensored and supports tool usage. The model is released under Apache‑2.0 and trained with a 4096 token context window.

Good at

  • Tool usage
  • Uncensored responses
  • Instruction following

Limits

  • No vision support
  • No certification
  • Limited language list

Best for

  • Chat assistants
  • Code generation
  • Tool‑integrated workflows

Who it’s for. Developers and researchers who need an uncensored instruction model with tool‑calling capability. The model is suitable for building AI assistants in business or technical domains.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_M3.7 GB 4.9 GB
Fits Get file →
IQ4_XS4.4 GB 5.6 GB
Fits Get file →
Q4_K_M4.9 GB 6.1 GB
Fits Get file →
Q5_K_M5.8 GB 7.0 GB
Fits Get file →
Q6_K6.7 GB 7.9 GB
Tight Get file →
Q8_08.7 GB 9.9 GB
Too big Get file →

For 8 GB VRAM, use IQ4_XS (4.43 GB, 6.3 GB memory at 8k context). For 16 GB VRAM, IQ4_XS or Q4_K_M (4.94 GB, 6.8 GB memory). For 24 GB VRAM, Q5_K_M (5.8 GB, 7.6 GB memory). All estimates are approximate.

What GPU do you need for Ektome granite 3.0 8b instruct PristinelyUncensored?

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: the best quant that fits is IQ3_M (3.7 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.8 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.5 GB in use).

Which Ektome granite 3.0 8b instruct PristinelyUncensored quant should you choose?

Q4_K_M is the usual starting point for Ektome granite 3.0 8b instruct PristinelyUncensored: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.7 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 IQ3_M at 3.7 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

Architecturegranite
Parameters8.17B
Layers40
Trained context4,096 tokens
KV cache (fp16)160 KB per token

Source

Quantized byZynerji
FamilyGranite
Licenseapache-2.0
Downloads (HF)895
Last updated2026-07-27

Frequently asked questions about Ektome granite 3.0 8b instruct PristinelyUncensored

How much VRAM does Ektome granite 3.0 8b instruct PristinelyUncensored need?

About 6.8 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Ektome granite 3.0 8b instruct PristinelyUncensored on an 8 GB GPU?

Yes, with Q5_K_M: the 5.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ektome granite 3.0 8b instruct PristinelyUncensored GGUF?

It depends on the quant: IQ3_M is 3.7 GB, IQ4_XS is 4.4 GB, Q4_K_M is 4.9 GB, Q5_K_M is 5.8 GB, Q6_K is 6.7 GB, Q8_0 is 8.7 GB.

What context length does Ektome granite 3.0 8b instruct PristinelyUncensored support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.3 GB at 8K and 0.7 GB at 4K.

Where can I download Ektome granite 3.0 8b instruct PristinelyUncensored GGUF?

The files are on Hugging Face in the Zynerji/Ektome-granite-3.0-8b-instruct-PristinelyUncensored repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Ektome granite 3.0 8b instruct PristinelyUncensored 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 quantization uses 4.43 GB file size and requires about 6.3 GB VRAM at 8k context.

Does this model support vision?

No, the model has no vision capability.

Is the model certified for safety?

No, it is not certified and has no n=2800 certificate.

Other GGUFs of granite-3.0-8b-instruct

Similar models

Browse all →

More from Zynerji

All by Zynerji →

More Granite models

All Granite →

Other small models

All small models →