GR

Granite-4.0-350M

GraniteGGUF by unslothUpdated 2025-10-28
Download on Hugging Face
Parameters352M
Context32K
Layers28
Architecturegranite
Smallest quant0.2 GB
Quick answer

Granite-4.0-350M needs about 1.7 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 19 quants, from 0.2 GB (IQ3_XXS) to 0.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Granite‑4.0‑350M – a lightweight 350 M‑parameter instruct model

Granite‑4.0‑350M is a 350 M‑parameter instruct model from the Granite family. It is finetuned on open‑source instruction datasets and synthetic data, and supports multilingual instruction following. The model is released under Apache 2.0.

Good at

  • Instruction following
  • Multilingual dialogue
  • Code and function‑calling tasks

Limits

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

Best for

  • On‑device instruction following
  • Fine‑tuning for specialized domains
  • Research on small‑scale LLMs

Who it’s for. Developers and researchers who need a compact, multilingual instruction model for on‑device deployment or fine‑tuning. The model is suitable for applications that require strong instruction following without large compute resources.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS0.2 GB 1.6 GB
Fits Get file →
Q3_K_S0.2 GB 1.6 GB
Fits Get file →
Q3_K_M0.2 GB 1.6 GB
Fits Get file →
Q3_K_XL0.2 GB 1.7 GB
Fits Get file →
IQ4_XS0.2 GB 1.7 GB
Fits Get file →
Q4_00.2 GB 1.7 GB
Fits Get file →
IQ4_NL0.2 GB 1.7 GB
Fits Get file →
Q4_K_S0.2 GB 1.7 GB
Fits Get file →
Q4_K_M0.2 GB 1.7 GB
Fits Get file →
Q4_K_XL0.2 GB 1.7 GB
Fits Get file →
Q4_10.2 GB 1.7 GB
Fits Get file →
Q5_K_S0.3 GB 1.7 GB
Fits Get file →
Q5_K_M0.3 GB 1.7 GB
Fits Get file →
Q5_K_XL0.3 GB 1.7 GB
Fits Get file →
Q6_K0.3 GB 1.7 GB
Fits Get file →
Q6_K_XL0.3 GB 1.8 GB
Fits Get file →
Q8_00.4 GB 1.8 GB
Fits Get file →
Q8_K_XL0.5 GB 2.0 GB
Fits Get file →
BF160.7 GB 2.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (≈1.7 GB file, 1.7 GB VRAM at 8 k context). For 4 GB VRAM, choose IQ3_XXS or Q3_K_S (≈0.17–0.2 GB file, 1.6 GB VRAM). Higher precision quants such as Q8_0 or BF16 need 1.8–2.1 GB VRAM and are recommended only if memory allows.

What GPU do you need for Granite-4.0-350M?

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 BF16 (0.7 GB file, about 2.1 GB in use).

Which Granite-4.0-350M quant should you choose?

Q4_K_M is the usual starting point for Granite-4.0-350M: it balances file size and quality well. Here it is a 0.2 GB file.

The Q8_0 file is 0.4 GB, about 1.6 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 IQ3_XXS at 0.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranite
Parameters352M
Layers28
Trained context32,768 tokens
KV cache (fp16)112 KB per token

Source

Quantized byunsloth
FamilyGranite
Licenseapache-2.0
Downloads (HF)6,743
Last updated2025-10-28

Frequently asked questions about Granite-4.0-350M

How much VRAM does Granite-4.0-350M need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 0.2 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-4.0-350M on an 8 GB GPU?

Yes, with BF16: the 0.7 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite-4.0-350M GGUF?

It depends on the quant: IQ3_XXS is 0.2 GB, Q3_K_S is 0.2 GB, Q3_K_M is 0.2 GB, Q3_K_XL is 0.2 GB, IQ4_XS is 0.2 GB, Q4_0 is 0.2 GB and 13 more.

What context length does Granite-4.0-350M support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Granite-4.0-350M GGUF?

The files are on Hugging Face in the unsloth/granite-4.0-350m-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-4.0-350M 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‑4.0‑350M on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quants requires about 1.7 GB VRAM at 8 k context. The model will run comfortably on 8 GB VRAM.

Does Granite‑4.0‑350M support image inputs?

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

What license applies to Granite‑4.0‑350M?

The model is released under the Apache 2.0 license.

Other GGUFs of granite-4.0-350m

Similar models

Browse all →

More from unsloth

All by unsloth →

More Granite models

All Granite →

Other tiny models

All tiny models →