GR

Granite 4.0 H Tiny

GraniteGGUF by bartowskiUpdated 2025-10-02
Download on Hugging Face
Parameters6.94B
Context1024K
Layers40
Architecturegranitehybrid
Smallest quant0.0 GB
Quick answer

Granite 4.0 H Tiny needs about 6.8 GB of memory at Q4_K_M (a 4.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 13.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.

Granite 4.0 H Tiny – 7.1B parameter long‑context instruction model

Granite 4.0 H Tiny is a 7.1B parameter instruct model with a 1,048,576 token context window. It is fine‑tuned from Granite‑4.0‑H‑Tiny‑Base using open source instruction data and internal synthetic datasets. The model supports multilingual instruction following and tool‑calling.

Good at

  • Long‑context instruction following
  • Tool‑calling and function integration
  • Multilingual dialogue

Limits

  • Large context requires high VRAM; 8k context needs ~6–9 GB RAM
  • No vision or audio modalities
  • Apache 2.0 license restricts commercial redistribution without attribution

Best for

  • Building AI assistants for business applications
  • Retrieval‑augmented generation pipelines
  • Code completion and function‑calling tasks

Who it’s for. Developers and enterprises looking for a compact, multilingual instruction model that can run on consumer GPUs. The model is suitable for building chatbots, RAG systems, and code‑related assistants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.6 GB
Fits Get file →
IQ2_M2.3 GB 4.8 GB
Fits Get file →
Q2_K2.6 GB 5.1 GB
Fits Get file →
Q2_K_L2.6 GB 5.1 GB
Fits Get file →
IQ3_XXS2.9 GB 5.4 GB
Fits Get file →
IQ3_XS3.0 GB 5.5 GB
Fits Get file →
Q3_K_S3.2 GB 5.7 GB
Fits Get file →
IQ3_M3.3 GB 5.8 GB
Fits Get file →
Q3_K_M3.3 GB 5.8 GB
Fits Get file →
Q3_K_L3.4 GB 5.9 GB
Fits Get file →
Q3_K_XL3.4 GB 6.0 GB
Fits Get file →
IQ4_XS3.8 GB 6.3 GB
Fits Get file →
IQ4_NL4.0 GB 6.5 GB
Fits Get file →
Q4_04.1 GB 6.6 GB
Fits Get file →
Q4_K_S4.2 GB 6.7 GB
Fits Get file →
Q4_K_M4.3 GB 6.8 GB
Fits Get file →
Q4_K_L4.3 GB 6.8 GB
Fits Get file →
Q4_14.4 GB 6.9 GB
Fits Get file →
Q5_K_S4.9 GB 7.4 GB
Tight Get file →
Q5_K_M5.0 GB 7.5 GB
Tight Get file →
Q5_K_L5.1 GB 7.6 GB
Tight Get file →
Q6_K5.8 GB 8.3 GB
Too big Get file →
Q6_K_L5.8 GB 8.3 GB
Too big Get file →
Q8_07.4 GB 9.9 GB
Too big Get file →
BF1613.9 GB 16.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (4.3 GB file, ~6.8 GB RAM at 8k context). If 12 GB VRAM is available, Q5_K_M (5.02 GB file, ~7.5 GB RAM) offers higher quality. For minimal memory, IQ2_M (2.29 GB file, ~4.8 GB RAM) is a viable option.

What GPU do you need for Granite 4.0 H Tiny?

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 the main file (0.0 GB file, about 2.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_XL (3.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_L (5.1 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.4 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.4 GB file, about 9.9 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (13.9 GB file, about 16.4 GB in use).

Which Granite 4.0 H Tiny quant should you choose?

Q4_K_M is the usual starting point for Granite 4.0 H Tiny: it balances file size and quality well. Here it is a 4.3 GB file.

The Q8_0 file is 7.4 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranitehybrid
Parameters6.94B (approximate, mixture of experts)
Layers40
Trained context1,048,576 tokens
KV cache (fp16)240 KB per token

Source

Quantized bybartowski
FamilyGranite
Licenseapache-2.0
Downloads (HF)3,882
Last updated2025-10-02

Frequently asked questions about Granite 4.0 H Tiny

How much VRAM does Granite 4.0 H Tiny need?

About 6.8 GB at Q4_K_M with an 8K context window. That is the 4.3 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 Tiny on an 8 GB GPU?

Yes, with Q5_K_L: the 5.1 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 4.0 H Tiny GGUF?

It depends on the quant: file is 0.0 GB, IQ2_M is 2.3 GB, Q2_K is 2.6 GB, Q2_K_L is 2.6 GB, IQ3_XXS is 2.9 GB, IQ3_XS is 3.0 GB and 19 more.

What context length does Granite 4.0 H Tiny 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 2.0 GB at 8K and 8.1 GB at 32K.

Where can I download Granite 4.0 H Tiny GGUF?

The files are on Hugging Face in the bartowski/ibm-granite_granite-4.0-h-tiny-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 Tiny 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 Tiny on 8 GB VRAM?

Yes, using Q4_K_M or Q4_K_L quantizations will fit within 8 GB VRAM and require approximately 6.8 GB RAM at 8k context.

Does this model support image inputs?

No, Granite 4.0 H Tiny is a text‑only model with no vision or audio capabilities.

What license applies to this model?

The model is released under the Apache 2.0 license, which allows commercial use with attribution.

Other GGUFs of granite-4.0-h-tiny

Similar models

Browse all →

More from bartowski

All by bartowski →

More Granite models

All Granite →

Other small models

All small models →