Granite 4.0 Tiny Preview needs about 6.6 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 2.2 GB (IQ2_M) to 13.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
Granite 4.0 Tiny Preview – 6.67B parameter MoE instruction model
Granite 4.0 Tiny Preview is a 6.67B parameter fine‑grained hybrid mixture‑of‑experts model. It is fine‑tuned for long‑context instruction following and supports 12 languages. The model is released under Apache 2.0.
Good at
- Long‑context instruction following
- Multilingual dialog
- Code and function‑calling tasks
Limits
- Large context requires high VRAM
- No vision support
- Requires llama.cpp or transformer source
Best for
- Chat assistants needing long context
- Document summarization
- Multilingual Q&A
Who it’s for. Developers and researchers building AI assistants that need to process long documents or conversations in multiple languages. The model is suitable for applications that can run llama.cpp or transformer source code.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 2.2 GB | 4.7 GB | Fits | Get file → | |
| Q2_K | 2.5 GB | 5.0 GB | Fits | Get file → | |
| Q2_K_L | 2.5 GB | 5.0 GB | Fits | Get file → | |
| IQ3_XXS | 2.7 GB | 5.3 GB | Fits | Get file → | |
| IQ3_XS | 2.9 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 3.0 GB | 5.5 GB | Fits | Get file → | |
| IQ3_M | 3.1 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_M | 3.1 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_L | 3.3 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_XL | 3.3 GB | 5.8 GB | Fits | Get file → | |
| IQ4_XS | 3.7 GB | 6.2 GB | Fits | Get file → | |
| IQ4_NL | 3.9 GB | 6.4 GB | Fits | Get file → | |
| Q4_0 | 3.9 GB | 6.4 GB | Fits | Get file → | |
| Q4_K_S | 4.0 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 4.1 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_L | 4.1 GB | 6.6 GB | Fits | Get file → | |
| Q4_1 | 4.3 GB | 6.8 GB | Fits | Get file → | |
| Q5_K_S | 4.7 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 4.8 GB | 7.3 GB | Tight | Get file → | |
| Q5_K_L | 4.8 GB | 7.3 GB | Tight | Get file → | |
| Q6_K | 5.5 GB | 8.0 GB | Too big | Get file → | |
| Q6_K_L | 5.6 GB | 8.1 GB | Too big | Get file → | |
| Q8_0 | 7.1 GB | 9.6 GB | Too big | Get file → | |
| BF16 | 13.4 GB | 15.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 3.91 GB, memory 6.4 GB at 8 k context). With 12 GB VRAM, Q4_K_M (4.12 GB, 6.6 GB) or Q5_K_S (4.66 GB, 7.2 GB) are suitable. For 16 GB VRAM, Q6_K (5.54 GB, 8 GB) or Q8_0 (7.1 GB, 9.6 GB) provide higher quality.
What GPU do you need for Granite 4.0 Tiny Preview?
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_XL (3.3 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.1 GB file, about 9.6 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (13.4 GB file, about 15.9 GB in use).
Which Granite 4.0 Tiny Preview quant should you choose?
Q4_K_M is the usual starting point for Granite 4.0 Tiny Preview: it balances file size and quality well. Here it is a 4.1 GB file.
The Q8_0 file is 7.1 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 IQ2_M at 2.2 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
Source
Frequently asked questions about Granite 4.0 Tiny Preview
How much VRAM does Granite 4.0 Tiny Preview need?
About 6.6 GB at Q4_K_M with an 8K context window. That is the 4.1 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 Tiny Preview on an 8 GB GPU?
Yes, with Q6_K: the 5.5 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Granite 4.0 Tiny Preview GGUF?
It depends on the quant: IQ2_M is 2.2 GB, Q2_K is 2.5 GB, Q2_K_L is 2.5 GB, IQ3_XXS is 2.7 GB, IQ3_XS is 2.9 GB, Q3_K_S is 3.0 GB and 18 more.
What context length does Granite 4.0 Tiny Preview 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 Tiny Preview GGUF?
The files are on Hugging Face in the bartowski/ibm-granite_granite-4.0-tiny-preview-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 Tiny Preview 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 Tiny Preview on 8 GB VRAM?
Yes, using the Q4_0 quantization which requires approximately 6.4 GB of VRAM at 8 k context.
Does this 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.