GR

granite4 h micro

GraniteGGUF by fqbUpdated 2025-11-20
Download on Hugging Face
Parameters3.19B
Context1024K
Layers40
Architecturegranitehybrid
Smallest quant1.9 GB
Quick answer

granite4 h micro needs about 5.1 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 1.9 GB (Q4_K_M) to 2.3 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

granite4 h micro is a 3.19B-parameter Granite model in GGUF format, quantized by fqb. Its trained context length is 1024K tokens. The repository has 2 quant files, from 1.9 GB (Q4_K_M) to 2.3 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.9 GB 5.1 GB
Fits Get file →
Q5_K_M2.3 GB 5.5 GB
Fits Get file →

What GPU do you need for granite4 h micro?

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 Q5_K_M (2.3 GB file, about 5.5 GB in use).

Which granite4 h micro quant should you choose?

Q4_K_M is the usual starting point for granite4 h micro: it balances file size and quality well. Here it is a 1.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegranitehybrid
Parameters3.19B
Layers40
Trained context1,048,576 tokens
KV cache (fp16)320 KB per token

Source

Quantized byfqb
FamilyGranite
Downloads (HF)5
Last updated2025-11-20

Frequently asked questions about granite4 h micro

How much VRAM does granite4 h micro need?

About 5.1 GB at Q4_K_M with an 8K context window. That is the 1.9 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 granite4 h micro on an 8 GB GPU?

Yes, with Q5_K_M: the 2.3 GB file needs about 5.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of granite4 h micro GGUF?

It depends on the quant: Q4_K_M is 1.9 GB, Q5_K_M is 2.3 GB.

What context length does granite4 h micro 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 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download granite4 h micro GGUF?

The files are on Hugging Face in the fqb/granite4-h-micro_GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from fqb

All by fqb →

More Granite models

All Granite →

Other tiny models

All tiny models →