GR

Granite 3.1 3b A800M Instruct

GraniteGGUF by bartowskiUpdated 2024-12-23
Download on Hugging Face
Parameters3.3B
Context128K
Layers32
Architecturegranitemoe
Smallest quant1.2 GB
Quick answer

Granite 3.1 3b A800M Instruct needs about 3.1 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 21 quants, from 1.2 GB (Q2_K) to 6.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

Granite 3.1 3b A800M Instruct – 3.3B parameter long‑context instruction model

Granite 3.1 3b A800M Instruct is a 3.3B parameter model trained 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
  • Retrieval‑augmented generation

Limits

  • No vision support
  • Requires 131072 token context
  • Apache‑2.0 license

Best for

  • Building AI assistants for business
  • Long document summarization
  • Code‑related tasks

Who it’s for. Developers and researchers needing a small‑to‑medium sized model with extended context for instruction‑based applications. The model is suitable for local deployment using llama.cpp or LM Studio.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.2 GB 2.3 GB
Fits Get file →
Q2_K_L1.3 GB 2.3 GB
Fits Get file →
IQ3_XS1.4 GB 2.4 GB
Fits Get file →
Q3_K_S1.5 GB 2.5 GB
Fits Get file →
IQ3_M1.5 GB 2.5 GB
Fits Get file →
Q3_K_M1.6 GB 2.6 GB
Fits Get file →
Q3_K_L1.7 GB 2.8 GB
Fits Get file →
Q3_K_XL1.8 GB 2.8 GB
Fits Get file →
IQ4_XS1.8 GB 2.8 GB
Fits Get file →
IQ4_NL1.9 GB 2.9 GB
Fits Get file →
Q4_01.9 GB 2.9 GB
Fits Get file →
Q4_K_S1.9 GB 2.9 GB
Fits Get file →
Q4_K_M2.0 GB 3.1 GB
Fits Get file →
Q4_K_L2.0 GB 3.1 GB
Fits Get file →
Q5_K_S2.3 GB 3.3 GB
Fits Get file →
Q5_K_M2.4 GB 3.4 GB
Fits Get file →
Q5_K_L2.4 GB 3.4 GB
Fits Get file →
Q6_K2.7 GB 3.8 GB
Fits Get file →
Q6_K_L2.7 GB 3.8 GB
Fits Get file →
Q8_03.5 GB 4.5 GB
Fits Get file →
F166.6 GB 7.6 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M (est. 3.1 GB) or Q5_K_S (est. 3.3 GB). For 4 GB VRAM, Q3_K_S (est. 2.5 GB) or Q2_K (est. 2.3 GB) are appropriate. Larger VRAM allows Q4_K_L (est. 3.1 GB) or Q5_K_M (est. 3.4 GB).

What GPU do you need for Granite 3.1 3b A800M 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 Q6_K_L (2.7 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.5 GB file, about 4.5 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.6 GB file, about 7.6 GB in use).

Which Granite 3.1 3b A800M Instruct quant should you choose?

Q4_K_M is the usual starting point for Granite 3.1 3b A800M Instruct: it balances file size and quality well. Here it is a 2.0 GB file.

The Q8_0 file is 3.5 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 Q2_K at 1.2 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

Architecturegranitemoe
Parameters3.3B (approximate, mixture of experts)
Layers32
Trained context131,072 tokens
KV cache (fp16)64 KB per token

Source

Quantized bybartowski
FamilyGranite
Licenseapache-2.0
Downloads (HF)2,761
Last updated2024-12-23

Frequently asked questions about Granite 3.1 3b A800M Instruct

How much VRAM does Granite 3.1 3b A800M Instruct need?

About 3.1 GB at Q4_K_M with an 8K context window. That is the 2.0 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 3b A800M Instruct on an 8 GB GPU?

Yes, with F16: the 6.6 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 3.1 3b A800M Instruct GGUF?

It depends on the quant: Q2_K is 1.2 GB, Q2_K_L is 1.3 GB, IQ3_XS is 1.4 GB, Q3_K_S is 1.5 GB, IQ3_M is 1.5 GB, Q3_K_M is 1.6 GB and 15 more.

What context length does Granite 3.1 3b A800M 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 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download Granite 3.1 3b A800M Instruct GGUF?

The files are on Hugging Face in the bartowski/granite-3.1-3b-a800m-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 3b A800M 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 3b A800M Instruct on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_S quantizations will fit within 8 GB VRAM with approximate memory usage of 3.1 GB or 3.3 GB respectively.

Does this model support vision tasks?

No, the model 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-3.1-3b-a800m-instruct

Similar models

Browse all →

More from bartowski

All by bartowski →

More Granite models

All Granite →

Other tiny models

All tiny models →