Granite 4.0 H Small BE needs about 22.3 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 20 quants, from 11.8 GB (Q2_K) to 128.8 GB (F32).
Granite 4.0 H Small BE – 32B long‑context instruction model
Granite 4.0 H Small BE is a 32B parameter model with a 1,048,576 token context. It is fine‑tuned for instruction following, tool‑calling, and multilingual dialogue. The model is released under Apache 2.0 and supports English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese.
Good at
- Instruction following
- Tool‑calling
- Multilingual dialogue
Limits
- No vision support
- Large VRAM required for higher quants
- License is Apache 2.0
Best for
- Enterprise AI assistants
- RAG and retrieval tasks
- Code completion with function calling
Who it’s for. Developers building AI assistants or enterprise applications that require robust instruction following and multilingual support. The model is suitable for users who can allocate sufficient GPU memory for the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 11.8 GB | 13.7 GB | Too big | Get file → | |
| Q3_K_S | 14.1 GB | 16.2 GB | Too big | Get file → | |
| Q3_K_M | 15.4 GB | 17.7 GB | Too big | Get file → | |
| Q3_K_L | 16.5 GB | 19.0 GB | Too big | Get file → | |
| IQ4_XS | 17.5 GB | 20.1 GB | Too big | Get file → | |
| Q4_0 | 18.3 GB | 21.0 GB | Too big | Get file → | |
| IQ4_NL | 18.4 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_S | 18.4 GB | 21.1 GB | Too big | Get file → | |
| Q4_K_M | 19.5 GB | 22.3 GB | Too big | Get file → | |
| MXFP4_MOE | 19.8 GB | 22.7 GB | Too big | Get file → | |
| Q4_1 | 20.3 GB | 23.2 GB | Too big | Get file → | |
| Q5_0 | 22.2 GB | 25.4 GB | Too big | Get file → | |
| Q5_K_S | 22.2 GB | 25.4 GB | Too big | Get file → | |
| Q5_K_M | 22.9 GB | 26.1 GB | Too big | Get file → | |
| Q5_1 | 24.2 GB | 27.6 GB | Too big | Get file → | |
| Q6_K | 26.5 GB | 30.1 GB | Too big | Get file → | |
| Q8_0 | 34.3 GB | 38.9 GB | Too big | Get file → | |
| F16 | 64.4 GB (2 parts) | 72.7 GB | Too big | Get file → | |
| BF16 | 64.4 GB (2 parts) | 72.7 GB | Too big | Get file → | |
| F32 | 128.8 GB (3 parts) | 144.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (21 GB memory estimate) or Q4_K_S (21 GB). For 12 GB VRAM, Q4_K_M (22.3 GB) is suitable. If you have 16 GB VRAM, Q5_0 (25.4 GB) or Q5_K_S (25.4 GB) can be used. Higher quants such as Q6_K or Q8_0 require more than 30 GB VRAM.
What GPU do you need for Granite 4.0 H Small BE?
These figures add the file size, an fp16 KV cache at an 8K context window 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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q2_K (11.8 GB file, about 13.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_1 (20.3 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.5 GB file, about 30.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (34.3 GB file, about 38.9 GB in use).
Which Granite 4.0 H Small BE quant should you choose?
Q4_K_M is the usual starting point for Granite 4.0 H Small BE: it balances file size and quality well. Here it is a 19.5 GB file.
The Q8_0 file is 34.3 GB, about 1.8 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 11.8 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 H Small BE
How much VRAM does Granite 4.0 H Small BE need?
About 22.3 GB at Q4_K_M with an 8K context window. That is the 19.5 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 Small BE on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Granite 4.0 H Small BE GGUF?
It depends on the quant: Q2_K is 11.8 GB, Q3_K_S is 14.1 GB, Q3_K_M is 15.4 GB, Q3_K_L is 16.5 GB, IQ4_XS is 17.5 GB, Q4_0 is 18.3 GB and 14 more.
What context length does Granite 4.0 H Small BE support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download Granite 4.0 H Small BE GGUF?
The files are on Hugging Face in the taronaeo/Granite-4.0-H-Small-BE-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 Small BE 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 Small BE on 8 GB VRAM?
The smallest quant that fits 8 GB VRAM is Q4_0, which estimates 21 GB memory usage at 8k context. It will not fit in 8 GB VRAM.
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.