Granite 4.0 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 15 quants, from 1.4 GB (IQ3_XS) to 6.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Granite 4.0 H Micro – 3.19B parameter long‑context model
Granite 4.0 H Micro is a 3.19B parameter instruction model with a 1,048,576 token context window. It is fine‑tuned for instruction following and tool‑calling, supporting multiple languages and enterprise use cases.
Good at
- Instruction following
- Tool‑calling
- Multilingual dialog
Limits
- No vision support
- License is Apache‑2.0
- Requires large VRAM for higher quantizations
Best for
- AI assistants
- Business applications
- RAG workflows
Who it’s for. Developers building AI assistants or enterprise applications that need robust instruction following and tool‑calling. The model supports a wide range of languages and can be fine‑tuned for additional languages.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XS | 1.4 GB | 4.6 GB | Fits | Get file → | |
| IQ3_S | 1.5 GB | 4.6 GB | Fits | Get file → | |
| IQ3_M | 1.5 GB | 4.7 GB | Fits | Get file → | |
| IQ4_XS | 1.8 GB | 4.9 GB | Fits | Get file → | |
| Q4_0 | 1.9 GB | 5.0 GB | Fits | Get file → | |
| IQ4_NL | 1.9 GB | 5.0 GB | Fits | Get file → | |
| Q4_K_S | 1.9 GB | 5.1 GB | Fits | Get file → | |
| Q4_K_M | 1.9 GB | 5.1 GB | Fits | Get file → | |
| Q5_0 | 2.2 GB | 5.4 GB | Fits | Get file → | |
| Q5_K_S | 2.2 GB | 5.4 GB | Fits | Get file → | |
| Q5_K_M | 2.3 GB | 5.5 GB | Fits | Get file → | |
| Q5_1 | 2.4 GB | 5.6 GB | Fits | Get file → | |
| Q6_K | 2.6 GB | 5.8 GB | Fits | Get file → | |
| Q8_0 | 3.4 GB | 6.6 GB | Fits | Get file → | |
| BF16 | 6.4 GB | 9.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_XS (1.76 GB file, ~4.9 GB memory at 8k context). If 12 GB VRAM is available, Q4_K_M (1.94 GB file, ~5.1 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (2.27 GB file, ~5.5 GB memory) provides higher precision.
What GPU do you need for Granite 4.0 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 Q6_K (2.6 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.4 GB file, about 6.6 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (6.4 GB file, about 9.6 GB in use).
Which Granite 4.0 H Micro quant should you choose?
Q4_K_M is the usual starting point for Granite 4.0 H Micro: it balances file size and quality well. Here it is a 1.9 GB file.
The Q8_0 file is 3.4 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 IQ3_XS at 1.4 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
Source
Frequently asked questions about Granite 4.0 H Micro
How much VRAM does Granite 4.0 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 Granite 4.0 H Micro on an 8 GB GPU?
Yes, with Q8_0: the 3.4 GB file needs about 6.6 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 Micro GGUF?
It depends on the quant: IQ3_XS is 1.4 GB, IQ3_S is 1.5 GB, IQ3_M is 1.5 GB, IQ4_XS is 1.8 GB, Q4_0 is 1.9 GB, IQ4_NL is 1.9 GB and 9 more.
What context length does Granite 4.0 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 Granite 4.0 H Micro GGUF?
The files are on Hugging Face in the tatsuyaaaaaaa/granite-4.0-h-micro-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 Micro 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 Micro on 8 GB VRAM?
Yes, using the IQ4_XS quantization which requires about 4.9 GB of VRAM at 8k context.
Does the model support vision tasks?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.