GR

Granite 4.0 H 350m Base

GraniteGGUF by ibm-graniteUpdated 2026-04-23
Download on Hugging Face
Parameters340M
Context1024K
Layers32
Architecturegranitehybrid
Smallest quant0.2 GB
Quick answer

Granite 4.0 H 350m Base needs about 1.5 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 15 quants, from 0.2 GB (Q2_K) to 0.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.2 GB.

Granite 4.0 H 350m Base – lightweight decoder-only LLM

Granite 4.0 H 350m Base is a 0.34 billion‑parameter decoder‑only model. It supports 1 048 576 context tokens and is optimized for speed and low memory usage. The model is released under Apache 2.0 and supports multiple languages.

Good at

  • Text summarization
  • Question answering
  • Code completion (FIM)

Limits

  • No vision support
  • Requires 1 048 576 context tokens
  • License is Apache 2.0

Best for

  • Edge devices with limited VRAM
  • Offline text generation
  • Privacy‑preserving applications

Who it’s for. Developers and researchers needing a small, fast language model for on‑device inference. The model is suitable for mobile, IoT, or embedded systems where resources are constrained.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.2 GB 1.5 GB
Fits Get file →
Q3_K_S0.2 GB 1.5 GB
Fits Get file →
Q3_K_M0.2 GB 1.5 GB
Fits Get file →
Q3_K_L0.2 GB 1.5 GB
Fits Get file →
Q4_00.2 GB 1.5 GB
Fits Get file →
Q4_K_S0.2 GB 1.5 GB
Fits Get file →
Q4_K_M0.2 GB 1.5 GB
Fits Get file →
Q4_10.2 GB 1.5 GB
Fits Get file →
Q5_00.2 GB 1.6 GB
Fits Get file →
Q5_K_S0.2 GB 1.6 GB
Fits Get file →
Q5_K_M0.3 GB 1.6 GB
Fits Get file →
Q5_10.3 GB 1.6 GB
Fits Get file →
Q6_K0.3 GB 1.6 GB
Fits Get file →
Q8_00.4 GB 1.7 GB
Fits Get file →
BF160.7 GB 2.0 GB
Fits Get file →

For 8 GB VRAM use Q4_K_M (0.22 GB file, ~1.5 GB RAM). For 4 GB VRAM use Q3_K_S (0.18 GB file, ~1.5 GB RAM). For 2 GB VRAM use Q2_K (0.16 GB file, ~1.5 GB RAM).

What GPU do you need for Granite 4.0 H 350m 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 BF16 (0.7 GB file, about 2.0 GB in use).

Which Granite 4.0 H 350m Base quant should you choose?

Q4_K_M is the usual starting point for Granite 4.0 H 350m Base: 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 Q2_K at 0.2 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

Architecturegranitehybrid
Parameters340M
Layers32
Trained context1,048,576 tokens
KV cache (fp16)96 KB per token

Source

Quantized byibm-granite
FamilyGranite
Licenseapache-2.0
Downloads (HF)579
Last updated2026-04-23

Frequently asked questions about Granite 4.0 H 350m Base

How much VRAM does Granite 4.0 H 350m Base need?

About 1.5 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 H 350m Base on an 8 GB GPU?

Yes, with BF16: the 0.7 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 4.0 H 350m Base GGUF?

It depends on the quant: Q2_K is 0.2 GB, Q3_K_S is 0.2 GB, Q3_K_M is 0.2 GB, Q3_K_L is 0.2 GB, Q4_0 is 0.2 GB, Q4_K_S is 0.2 GB and 9 more.

What context length does Granite 4.0 H 350m Base support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.8 GB at 8K and 3.2 GB at 32K.

Where can I download Granite 4.0 H 350m Base GGUF?

The files are on Hugging Face in the ibm-granite/granite-4.0-h-350m-base-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 H 350m 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 4.0 H 350m Base on 8 GB VRAM?

Yes, the Q4_K_M quantization uses about 1.5 GB of VRAM at 8 k context.

Does the model support image input?

No, the model is decoder‑only and has no vision capability.

What license does the model use?

The model is released under the Apache 2.0 license.

Other GGUFs of granite-4.0-h-350m-base

Similar models

Browse all →

More from ibm-granite

All by ibm-granite →

More Granite models

All Granite →

Other tiny models

All tiny models →