GR

Granite 4.0 H Tiny

GraniteGGUF by ibm-graniteUpdated 2026-04-23
Download on Hugging Face
Parameters6.94B
Context1024K
Layers40
Architecturegranitehybrid
Smallest quant2.6 GB
Quick answer

Granite 4.0 H Tiny needs about 6.7 GB of memory at Q4_K_M (a 4.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 2.6 GB (Q2_K) 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 – 6.9B parameter long‑context instruct model

Granite 4.0 H Tiny is a 6.9 B parameter model trained for long‑context instruction following. It supports up to 1 048 576 context tokens and includes tool‑calling and retrieval‑augmented generation. The model is released under Apache 2.0 and is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • Tool‑calling
  • Multilingual dialogue

Limits

  • Large context requires high VRAM
  • No vision support
  • Requires Apache 2.0 license

Best for

  • Building AI assistants
  • Enterprise business applications
  • Code completion tasks

Who it’s for. Developers and data scientists who need a compact, long‑context model for instruction‑driven applications. The model is suitable for users who can manage the memory requirements of the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.6 GB 5.1 GB
Fits Get file →
Q3_K_S3.1 GB 5.6 GB
Fits Get file →
Q3_K_M3.4 GB 5.9 GB
Fits Get file →
Q3_K_L3.6 GB 6.1 GB
Fits Get file →
Q4_04.0 GB 6.5 GB
Fits Get file →
Q4_K_S4.0 GB 6.5 GB
Fits Get file →
Q4_K_M4.2 GB 6.7 GB
Fits Get file →
Q4_14.4 GB 6.9 GB
Fits Get file →
Q5_04.8 GB 7.3 GB
Tight Get file →
Q5_K_S4.8 GB 7.3 GB
Tight Get file →
Q5_K_M4.9 GB 7.5 GB
Tight Get file →
Q5_15.2 GB 7.7 GB
Tight Get file →
Q6_K5.7 GB 8.2 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 (≈6.7 GB) or Q4_0 (≈6.5 GB). For 12 GB VRAM, Q5_K_M (≈7.5 GB) or Q5_1 (≈7.7 GB) are suitable. Larger VRAM allows higher‑quality Q6_K or Q8_0 quantizations.

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q3_K_M (3.4 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (5.2 GB file, about 7.7 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 4.2 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 Q2_K at 2.6 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
Parameters6.94B (approximate, mixture of experts)
Layers40
Trained context1,048,576 tokens
KV cache (fp16)240 KB per token

Source

Quantized byibm-granite
FamilyGranite
Licenseapache-2.0
Downloads (HF)9,315
Last updated2026-04-23

Frequently asked questions about Granite 4.0 H Tiny

How much VRAM does Granite 4.0 H Tiny need?

About 6.7 GB at Q4_K_M with an 8K context window. That is the 4.2 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 Tiny on an 8 GB GPU?

Yes, with Q5_1: the 5.2 GB file needs about 7.7 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: Q2_K is 2.6 GB, Q3_K_S is 3.1 GB, Q3_K_M is 3.4 GB, Q3_K_L is 3.6 GB, Q4_0 is 4.0 GB, Q4_K_S is 4.0 GB and 9 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 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_0 quantizations which require about 6.5–6.7 GB of VRAM at 8k context.

Does the model support vision tasks?

No, Granite 4.0 H Tiny is a text‑only model and does not include vision capabilities.

What license applies to this model?

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

Other GGUFs of granite-4.0-h-tiny

Similar models

Browse all →

More from ibm-granite

All by ibm-granite →

More Granite models

All Granite →

Other small models

All small models →