Granite 4.0 Micro needs about 6.0 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 6.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 13.4 GB.
Granite 4.0 Micro – 3.4B parameter long‑context instruction model
Granite 4.0 Micro is a 3.4B parameter model trained on 131072 context tokens. It is fine‑tuned from Granite‑4.0‑Micro‑Base with instruction datasets and reinforcement learning. The model supports multilingual instruction following and tool‑calling.
Good at
- Instruction following
- Tool‑calling
- Multilingual dialogue
Limits
- Large context requires high VRAM
- No vision support
- Apache 2.0 license
Best for
- Enterprise AI assistants
- Tool‑enabled LLM agents
- RAG applications
Who it’s for. Developers building AI assistants or agents that need robust instruction following and tool integration. The model is suitable for businesses that require a multilingual, open‑source foundation with a permissive license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.9 GB | Fits | Get file → | |
| IQ2_M | 1.2 GB | 5.1 GB | Fits | Get file → | |
| Q2_K | 1.4 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XXS | 1.4 GB | 5.2 GB | Fits | Get file → | |
| Q2_K_L | 1.4 GB | 5.3 GB | Fits | Get file → | |
| IQ3_XS | 1.5 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 1.6 GB | 5.4 GB | Fits | Get file → | |
| IQ3_M | 1.6 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_M | 1.7 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_L | 1.9 GB | 5.7 GB | Fits | Get file → | |
| IQ4_XS | 1.9 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_XL | 1.9 GB | 5.8 GB | Fits | Get file → | |
| IQ4_NL | 2.0 GB | 5.8 GB | Fits | Get file → | |
| Q4_0 | 2.0 GB | 5.8 GB | Fits | Get file → | |
| Q4_K_S | 2.0 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 6.0 GB | Fits | Get file → | |
| Q4_K_L | 2.2 GB | 6.0 GB | Fits | Get file → | |
| Q4_1 | 2.2 GB | 6.0 GB | Fits | Get file → | |
| Q5_K_S | 2.4 GB | 6.2 GB | Fits | Get file → | |
| Q5_K_M | 2.4 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_L | 2.5 GB | 6.4 GB | Fits | Get file → | |
| Q6_K | 2.8 GB | 6.7 GB | Fits | Get file → | |
| Q6_K_L | 2.9 GB | 6.7 GB | Fits | Get file → | |
| Q8_0 | 3.6 GB | 7.5 GB | Tight | Get file → | |
| BF16 | 6.8 GB | 10.7 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 2.1 GB, memory 6 GB). For 12 GB VRAM Q5_K_M (2.44 GB, 6.3 GB). For 16 GB VRAM Q6_K (2.8 GB, 6.7 GB). Larger VRAM allows higher‑quality quants like Q8_0.
What GPU do you need for Granite 4.0 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: the best quant that fits is the main file (0.0 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_1 (2.2 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (6.8 GB file, about 10.7 GB in use).
Which Granite 4.0 Micro quant should you choose?
Q4_K_M is the usual starting point for Granite 4.0 Micro: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.6 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
Source
Frequently asked questions about Granite 4.0 Micro
How much VRAM does Granite 4.0 Micro need?
About 6.0 GB at Q4_K_M with an 8K context window. That is the 2.1 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 Micro on an 8 GB GPU?
Yes, with Q8_0: the 3.6 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Granite 4.0 Micro GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 1.2 GB, Q2_K is 1.4 GB, IQ3_XXS is 1.4 GB, Q2_K_L is 1.4 GB, IQ3_XS is 1.5 GB and 19 more.
What context length does Granite 4.0 Micro support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.4 GB at 8K and 13.4 GB at 32K.
Where can I download Granite 4.0 Micro GGUF?
The files are on Hugging Face in the bartowski/ibm-granite_granite-4.0-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 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 Micro on 8 GB VRAM?
Yes, use the Q4_K_M quant which requires about 6 GB of VRAM at 8k context.
Does the model support vision tasks?
No, Granite 4.0 Micro is a text‑only model.
What license does the model use?
The model is released under the Apache 2.0 license.