GR

Granite 3.1 2b Instruct

GraniteGGUF by bartowskiUpdated 2024-12-23
Download on Hugging Face
Parameters2.53B
Context128K
Layers40
Architecturegranite
Smallest quant0.9 GB
Quick answer

Granite 3.1 2b Instruct 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 22 quants, from 0.9 GB (IQ2_M) to 5.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.7 GB.

Granite 3.1 2B Instruct – 2.53B parameter long‑context instruction model

Granite 3.1 2B Instruct is a 2.53B parameter model fine‑tuned for long‑context instruction following. It supports 131072 token context and is released under Apache‑2.0. The model is available in multiple GGUF quantizations for llama.cpp.

Good at

  • Long‑context instruction following
  • Multilingual dialog (12 supported languages)
  • Code and function‑calling tasks

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • License is Apache‑2.0

Best for

  • Building AI assistants for business
  • Long document summarization
  • Retrieval‑augmented generation

Who it’s for. Developers and researchers needing a compact, long‑context instruction model. The model is suitable for local deployment with llama.cpp or LM Studio.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M0.9 GB 2.1 GB
Fits Get file →
Q2_K1.0 GB 2.1 GB
Fits Get file →
Q2_K_L1.0 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_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 →
Q3_K_XL1.4 GB 2.6 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_K_L1.6 GB 2.7 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 →
Q5_K_L1.8 GB 3.0 GB
Fits Get file →
Q6_K2.1 GB 3.3 GB
Fits Get file →
Q6_K_L2.1 GB 3.3 GB
Fits Get file →
Q8_02.7 GB 3.9 GB
Fits Get file →
F165.1 GB 6.2 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 1.55 GB, estimated 2.7 GB memory). For 4 GB VRAM, use Q2_K (file size 0.98 GB, estimated 2.1 GB memory). For higher quality with 12 GB VRAM, use Q5_K_M (file size 1.8 GB, estimated 3 GB memory).

What GPU do you need for Granite 3.1 2b 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: the best quant that fits is Q8_0 (2.7 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.7 GB file, about 3.9 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.1 GB file, about 6.2 GB in use).

Which Granite 3.1 2b Instruct quant should you choose?

Q4_K_M is the usual starting point for Granite 3.1 2b Instruct: it balances file size and quality well. Here it is a 1.5 GB file.

The Q8_0 file is 2.7 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 IQ2_M at 0.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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

Source

Quantized bybartowski
FamilyGranite
Licenseapache-2.0
Downloads (HF)4,247
Last updated2024-12-23

Frequently asked questions about Granite 3.1 2b Instruct

How much VRAM does Granite 3.1 2b Instruct 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 3.1 2b Instruct on an 8 GB GPU?

Yes, with F16: the 5.1 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 3.1 2b Instruct GGUF?

It depends on the quant: IQ2_M is 0.9 GB, Q2_K is 1.0 GB, Q2_K_L is 1.0 GB, IQ3_XS is 1.1 GB, Q3_K_S is 1.1 GB, IQ3_M is 1.2 GB and 16 more.

What context length does Granite 3.1 2b Instruct 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 3.1 2b Instruct GGUF?

The files are on Hugging Face in the bartowski/granite-3.1-2b-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 Granite 3.1 2b 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 Granite 3.1 2B Instruct on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires approximately 2.7 GB memory at 8k context.

Does this model support vision tasks?

No, the model does not have vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of granite-3.1-2b-instruct

Similar models

Browse all →

More from bartowski

All by bartowski →

More Granite models

All Granite →

Other tiny models

All tiny models →