GR

Granite 3.0 8b Base

GraniteGGUF by mradermacherUpdated 2025-01-15
Download on Hugging Face
Parameters8.17B
Context4K
Layers40
Architecturegranite
Smallest quant1.8 GB
Quick answer

Granite 3.0 8b Base 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 24 quants, from 1.8 GB (IQ1_S) to 6.7 GB (Q6_K).

Granite 3.0 8b Base – a decoder‑only language model

Granite 3.0 8b Base is a decoder‑only dense transformer with 8.17 billion parameters. It supports 12 languages and is trained on 12 trillion tokens across two stages. The model is released under Apache 2.0.

Good at

  • Summarization
  • Question‑answering
  • Text classification

Limits

  • No vision support
  • Context limited to 4096 tokens
  • Requires 8 k context for memory estimates

Best for

  • Chatbots on edge devices
  • Fine‑tuning for specific domains
  • Rapid prototyping of text generation

Who it’s for. Developers and researchers needing a multilingual text‑to‑text model that can be run locally. The model is suitable for building lightweight inference pipelines and for fine‑tuning on custom datasets.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.8 GB 3.0 GB
Fits Get file →
IQ1_M2.0 GB 3.2 GB
Fits Get file →
IQ2_XXS2.3 GB 3.4 GB
Fits Get file →
IQ2_XS2.5 GB 3.7 GB
Fits Get file →
IQ2_S2.6 GB 3.8 GB
Fits Get file →
IQ2_M2.8 GB 4.0 GB
Fits Get file →
Q2_K_S2.9 GB 4.1 GB
Fits Get file →
Q2_K3.1 GB 4.3 GB
Fits Get file →
IQ3_XXS3.2 GB 4.4 GB
Fits Get file →
IQ3_XS3.4 GB 4.6 GB
Fits Get file →
Q3_K_S3.6 GB 4.8 GB
Fits Get file →
IQ3_S3.6 GB 4.8 GB
Fits Get file →
IQ3_M3.7 GB 4.9 GB
Fits Get file →
Q3_K_M4.0 GB 5.2 GB
Fits Get file →
Q3_K_L4.3 GB 5.5 GB
Fits Get file →
IQ4_XS4.4 GB 5.6 GB
Fits Get file →
Q4_04.7 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_K_S5.6 GB 6.8 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 →

For 8 GB VRAM, use IQ1_S (1.84 GB, 3.7 GB memory at 8 k context) or IQ1_M (2 GB, 3.8 GB). For 12 GB VRAM, IQ2_S (2.62 GB, 4.5 GB) or Q2_K (3.1 GB, 4.9 GB) are good choices. For 16 GB VRAM, Q3_K_M (4 GB, 5.8 GB) or Q4_K_M (4.94 GB, 6.8 GB) provide higher quality.

What GPU do you need for Granite 3.0 8b Base?

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 IQ1_M (2.0 GB file, about 3.8 GB in use).
  • 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_K_M (5.8 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.5 GB in use).

Which Granite 3.0 8b Base quant should you choose?

Q4_K_M is the usual starting point for Granite 3.0 8b Base: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ1_S at 1.8 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 bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)1,257
Last updated2025-01-15

Frequently asked questions about Granite 3.0 8b Base

How much VRAM does Granite 3.0 8b Base 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 Granite 3.0 8b Base 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 Granite 3.0 8b Base GGUF?

It depends on the quant: IQ1_S is 1.8 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 18 more.

What context length does Granite 3.0 8b Base 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 Base GGUF?

The files are on Hugging Face in the mradermacher/granite-3.0-8b-base-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 3.0 8b Base 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 Base on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations; they fit within 8 GB VRAM and use about 3.7–3.8 GB memory at 8 k context.

Does the model support image inputs?

No, the model is text‑only and has no vision capabilities.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of granite-3.0-8b-base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other small models

All small models →