GR

Granite 3.0 1b A400M Instruct

GraniteGGUF by mradermacherUpdated 2024-11-16
Download on Hugging Face
Parameters1.33B
Context4K
Layers24
Architecturegranitemoe
Smallest quant0.5 GB
Quick answer

Granite 3.0 1b A400M Instruct needs about 1.7 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 0.5 GB (Q2_K) to 2.7 GB (F16).

Granite 3.0 1b A400M Instruct – 1.33B parameter MoE model

Granite 3.0 1b A400M Instruct is a 1.33B parameter decoder‑only sparse Mixture of Experts transformer. It is fine‑tuned from Granite‑3.0‑1B‑A400M‑Base with instruction datasets and reinforcement learning. The model supports 12 languages and is licensed under Apache‑2.0.

Good at

  • Instruction following
  • Multilingual dialogue
  • Function‑calling

Limits

  • No vision support
  • Requires 8k context for full performance
  • License is Apache‑2.0

Best for

  • Building AI assistants
  • Business application chatbots
  • Code‑related tasks

Who it’s for. Developers and researchers who need a lightweight, instruction‑tuned MoE model for multilingual applications. The model is suitable for teams that can manage the 8k context requirement and comply with the Apache‑2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.5 GB 1.2 GB
Fits Get file →
Q3_K_S0.6 GB 1.3 GB
Fits Get file →
Q3_K_M0.7 GB 1.4 GB
Fits Get file →
Q3_K_L0.7 GB 1.4 GB
Fits Get file →
IQ4_XS0.7 GB 1.4 GB
Fits Get file →
Q4_00.8 GB 1.5 GB
Fits Get file →
Q4_K_S0.8 GB 1.5 GB
Fits Get file →
Q4_K_M0.8 GB 1.5 GB
Fits Get file →
Q5_K_S0.9 GB 1.6 GB
Fits Get file →
Q5_K_M1.0 GB 1.7 GB
Fits Get file →
Q6_K1.1 GB 1.8 GB
Fits Get file →
Q8_01.4 GB 2.1 GB
Fits Get file →
F162.7 GB 3.4 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.82 GB file, 1.7 GB memory). For 4 GB VRAM, use Q3_K_S (0.6 GB file, 1.5 GB memory). For 2 GB VRAM, use Q2_K (0.51 GB file, 1.4 GB memory). Estimates are approximate.

What GPU do you need for Granite 3.0 1b A400M 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 F16 (2.7 GB file, about 3.6 GB in use).

Which Granite 3.0 1b A400M Instruct quant should you choose?

Q4_K_M is the usual starting point for Granite 3.0 1b A400M Instruct: it balances file size and quality well. Here it is a 0.8 GB file.

The Q8_0 file is 1.4 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 0.5 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

Architecturegranitemoe
Parameters1.33B (approximate, mixture of experts)
Layers24
Trained context4,096 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)561
Last updated2024-11-16

Frequently asked questions about Granite 3.0 1b A400M Instruct

How much VRAM does Granite 3.0 1b A400M Instruct need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 0.8 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 1b A400M Instruct on an 8 GB GPU?

Yes, with F16: the 2.7 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 3.0 1b A400M Instruct GGUF?

It depends on the quant: Q2_K is 0.5 GB, Q3_K_S is 0.6 GB, Q3_K_M is 0.7 GB, Q3_K_L is 0.7 GB, IQ4_XS is 0.7 GB, Q4_0 is 0.8 GB and 7 more.

What context length does Granite 3.0 1b A400M 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 0.4 GB at 8K and 0.2 GB at 4K.

Where can I download Granite 3.0 1b A400M Instruct GGUF?

The files are on Hugging Face in the mradermacher/granite-3.0-1b-a400m-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 1b A400M 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 1b A400M Instruct on 8 GB VRAM?

Yes, the Q4_K_M quant uses 1.7 GB of VRAM at 8k context, which fits within 8 GB. The file size is 0.82 GB.

Does the model support image inputs?

No, the model has no vision support. It is designed for text-only tasks.

What license does the model use?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Other GGUFs of granite-3.0-1b-a400m-instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other tiny models

All tiny models →