GR

granite-3.0-8b-instruct

GraniteGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters8.17B
Context4K
Layers40
Architecturegranite
Smallest quant2.5 GB
Quick answer

granite-3.0-8b-instruct needs about 6.7 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 27 quants, from 2.5 GB (IQ2_XXS) to 16.3 GB (BF16).

Granite‑3.0‑8B‑Instruct – a decoder‑only instruct model

Granite‑3.0‑8B‑Instruct is a 8.17 billion‑parameter language model built on the Granite architecture. It supports text‑to‑text generation tasks such as summarization, classification, and question answering. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.

Good at

  • Text generation
  • Instruction following
  • Tool‑use support

Limits

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

Best for

  • Chatbots that need instruction compliance
  • Automated content creation
  • Code generation with tool integration

Who it’s for. Developers and researchers who need a lightweight instruct model for text‑only applications. The model is suitable for fine‑tuning on domain‑specific data or for deployment in resource‑constrained environments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS2.5 GB 3.6 GB
Fits Get file →
IQ2_XS2.7 GB 3.9 GB
Fits Get file →
IQ2_S2.8 GB 4.0 GB
Fits Get file →
IQ2_M2.9 GB 4.1 GB
Fits Get file →
Q2_K_S3.0 GB 4.2 GB
Fits Get file →
Q2_K_M3.1 GB 4.2 GB
Fits Get file →
IQ3_XXS3.3 GB 4.5 GB
Fits Get file →
IQ3_XS3.4 GB 4.6 GB
Fits Get file →
IQ3_M3.8 GB 5.0 GB
Fits Get file →
IQ3_S3.8 GB 5.0 GB
Fits Get file →
Q3_K_S3.9 GB 5.1 GB
Fits Get file →
Q3_K_M4.0 GB 5.1 GB
Fits Get file →
IQ4_XS4.4 GB 5.6 GB
Fits Get file →
Q4_04.6 GB 5.8 GB
Fits Get file →
IQ4_NL4.7 GB 5.8 GB
Fits Get file →
Q4_K_S4.7 GB 5.9 GB
Fits Get file →
Q4_K_M4.9 GB 6.1 GB
Fits Get file →
Q4_15.1 GB 6.3 GB
Fits Get file →
Q5_05.6 GB 6.8 GB
Fits Get file →
Q5_K_S5.7 GB 6.9 GB
Fits Get file →
Q5_K_M5.8 GB 7.0 GB
Fits Get file →
Q5_16.1 GB 7.3 GB
Tight Get file →
Q6_K_M6.7 GB 7.9 GB
Tight Get file →
Q8_08.7 GB 9.9 GB
Too big Get file →
BF1611.6 GB 12.8 GB
Too big Get file →
F1611.6 GB 12.8 GB
Too big Get file →
BF1616.3 GB 17.5 GB
Too big Get file →

For 8 GB VRAM, the Q4_K_M quant (4.9 GB file, 6.7 GB memory at 8 k context) is a good balance. If memory is tighter, use Q3_K_M (3.97 GB file, 5.8 GB memory). For maximum quality and available memory, Q8_0 (8.68 GB file, 10.5 GB memory) is recommended.

What GPU do you need for granite-3.0-8b-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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.0 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (6.1 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.5 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (11.6 GB file, about 13.5 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (16.3 GB file, about 18.2 GB in use).

Which granite-3.0-8b-instruct quant should you choose?

Q4_K_M is the usual starting point for granite-3.0-8b-instruct: 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 IQ2_XXS at 2.5 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
Parameters8.17B
Layers40
Trained context4,096 tokens
KV cache (fp16)160 KB per token

Source

Quantized byMungert
FamilyGranite
Licenseapache-2.0
Downloads (HF)483
Last updated2025-09-24

Frequently asked questions about granite-3.0-8b-instruct

How much VRAM does granite-3.0-8b-instruct need?

About 6.7 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 granite-3.0-8b-instruct on an 8 GB GPU?

Yes, with Q5_1: 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 granite-3.0-8b-instruct GGUF?

It depends on the quant: IQ2_XXS is 2.5 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB, Q2_K_S is 3.0 GB, Q2_K_M is 3.1 GB and 21 more.

What context length does granite-3.0-8b-instruct 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 granite-3.0-8b-instruct GGUF?

The files are on Hugging Face in the Mungert/granite-3.0-8b-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-3.0-8b-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‑3.0‑8B‑Instruct on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 6.7 GB memory at 8 k context, which fits within 8 GB VRAM.

Does the model support vision tasks?

No, the model is text‑only and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of granite-3.0-8b-base

Similar models

Browse all →

More from Mungert

All by Mungert →

More Granite models

All Granite →

Other small models

All small models →