GR

Granite 3.3 2b Instruct Heretic Safety Defiltered

GraniteGGUF by mradermacherUpdated 2026-04-07
Download on Hugging Face
Parameters2.53B
Context128K
Layers40
Architecturegranite
Smallest quant0.0 GB
Quick answer

Granite 3.3 2b Instruct Heretic Safety Defiltered needs about 2.7 GB of memory at Q4_K_M (a 1.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 2.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Granite 3.3 2b Instruct Heretic Safety Defiltered – 2.53B parameter instruction model

Granite 3.3 2b Instruct Heretic Safety Defiltered is a 2.53B parameter language model with a 131072 token context window. It is fine‑tuned for instruction following and reasoning. The model is released under Apache‑2.0.

Good at

  • Instruction following
  • Reasoning tasks
  • Long‑context handling

Limits

  • No vision support
  • Requires 131072 token context
  • License is Apache‑2.0

Best for

  • AI assistants
  • Business instruction workflows
  • Long document summarization

Who it’s for. Developers building AI assistants that need robust instruction following and reasoning. The model is suitable for applications requiring a large context window and is available under a permissive license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.2 GB
Fits Get file →
IQ1_S0.6 GB 1.8 GB
Fits Get file →
IQ1_M0.6 GB 1.8 GB
Fits Get file →
IQ2_XXS0.7 GB 1.9 GB
Fits Get file →
IQ2_XS0.8 GB 2.0 GB
Fits Get file →
IQ2_S0.8 GB 2.0 GB
Fits Get file →
IQ2_M0.9 GB 2.1 GB
Fits Get file →
Q2_K_S0.9 GB 2.1 GB
Fits Get file →
Q2_K1.0 GB 2.1 GB
Fits Get file →
IQ3_XXS1.0 GB 2.2 GB
Fits Get file →
IQ3_XS1.1 GB 2.2 GB
Fits Get file →
Q3_K_S1.1 GB 2.3 GB
Fits Get file →
IQ3_S1.1 GB 2.3 GB
Fits Get file →
IQ3_M1.2 GB 2.3 GB
Fits Get file →
Q3_K_M1.3 GB 2.4 GB
Fits Get file →
Q3_K_L1.4 GB 2.5 GB
Fits Get file →
IQ4_XS1.4 GB 2.6 GB
Fits Get file →
IQ4_NL1.5 GB 2.6 GB
Fits Get file →
Q4_01.5 GB 2.6 GB
Fits Get file →
Q4_K_S1.5 GB 2.6 GB
Fits Get file →
Q4_K_M1.5 GB 2.7 GB
Fits Get file →
Q4_11.6 GB 2.8 GB
Fits Get file →
Q5_K_S1.8 GB 2.9 GB
Fits Get file →
Q5_K_M1.8 GB 3.0 GB
Fits Get file →
Q6_K2.1 GB 3.3 GB
Fits Get file →

For 8 GB VRAM, use IQ2_XS (0.79 GB, 2 GB memory) or Q2_K (0.98 GB, 2.1 GB memory). For 12 GB VRAM, IQ3_XS (1.08 GB, 2.2 GB memory) or Q3_K_S (1.13 GB, 2.3 GB memory) are suitable. Higher quants such as Q5_K_M (1.8 GB, 3 GB memory) require more VRAM.

What GPU do you need for Granite 3.3 2b Instruct Heretic Safety Defiltered?

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 Q6_K (2.1 GB file, about 3.3 GB in use).

Which Granite 3.3 2b Instruct Heretic Safety Defiltered quant should you choose?

Q4_K_M is the usual starting point for Granite 3.3 2b Instruct Heretic Safety Defiltered: it balances file size and quality well. Here it is a 1.5 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

Architecturegranite
Parameters2.53B
Layers40
Trained context131,072 tokens
KV cache (fp16)80 KB per token

Frequently asked questions about Granite 3.3 2b Instruct Heretic Safety Defiltered

How much VRAM does Granite 3.3 2b Instruct Heretic Safety Defiltered need?

About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.5 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 Granite 3.3 2b Instruct Heretic Safety Defiltered on an 8 GB GPU?

Yes, with Q6_K: the 2.1 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 3.3 2b Instruct Heretic Safety Defiltered GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.6 GB, IQ1_M is 0.6 GB, IQ2_XXS is 0.7 GB, IQ2_XS is 0.8 GB, IQ2_S is 0.8 GB and 19 more.

What context length does Granite 3.3 2b Instruct Heretic Safety Defiltered support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.7 GB at 32K.

Where can I download Granite 3.3 2b Instruct Heretic Safety Defiltered GGUF?

The files are on Hugging Face in the mradermacher/granite-3.3-2b-instruct-heretic-safety-defiltered-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 Granite 3.3 2b Instruct Heretic Safety Defiltered 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, with IQ2_XS or Q2_K quant files the estimated VRAM usage is around 2 GB at 8k context.

Does the model support vision tasks?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of granite-3.3-2b-instruct-heretic-safety-defiltered

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other tiny models

All tiny models →