Granite 4.0 H 3b Ar needs about 5.2 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 2.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Granite 4.0 H 3b Ar – 3.4B multilingual LLM for English and Arabic
Granite 4.0 H 3b Ar is a 3.4B‑parameter instruct model built by IBM Research and MBZUAI. It supports English and Arabic, including MSA and several dialects. The model is designed for efficient deployment in resource‑constrained environments.
Good at
- Arabic dialect understanding
- English‑Arabic cross‑lingual tasks
- Tool‑use instruction following
Limits
- No vision support
- License is apache‑2.0
- Context length 8,192 tokens
Best for
- Multilingual chatbots
- Arabic dialect translation
- Cross‑lingual QA
Who it’s for. Developers needing a compact multilingual model for English and Arabic. Ideal for edge devices or low‑budget servers where VRAM is limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.2 GB | Fits | Get file → | |
| IQ1_S | 0.8 GB | 4.0 GB | Fits | Get file → | |
| IQ1_M | 0.9 GB | 4.1 GB | Fits | Get file → | |
| IQ2_XXS | 1.0 GB | 4.2 GB | Fits | Get file → | |
| IQ2_XS | 1.1 GB | 4.3 GB | Fits | Get file → | |
| IQ2_S | 1.1 GB | 4.3 GB | Fits | Get file → | |
| IQ2_M | 1.2 GB | 4.4 GB | Fits | Get file → | |
| Q2_K_S | 1.2 GB | 4.4 GB | Fits | Get file → | |
| Q2_K | 1.3 GB | 4.5 GB | Fits | Get file → | |
| IQ3_XXS | 1.4 GB | 4.6 GB | Fits | Get file → | |
| IQ3_XS | 1.5 GB | 4.7 GB | Fits | Get file → | |
| IQ3_S | 1.5 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_S | 1.5 GB | 4.7 GB | Fits | Get file → | |
| IQ3_M | 1.6 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_M | 1.6 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_L | 1.7 GB | 4.9 GB | Fits | Get file → | |
| IQ4_XS | 1.9 GB | 5.1 GB | Fits | Get file → | |
| IQ4_NL | 2.0 GB | 5.2 GB | Fits | Get file → | |
| Q4_0 | 2.0 GB | 5.2 GB | Fits | Get file → | |
| Q4_K_S | 2.0 GB | 5.2 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 5.2 GB | Fits | Get file → | |
| Q4_1 | 2.2 GB | 5.4 GB | Fits | Get file → | |
| Q5_K_S | 2.4 GB | 5.6 GB | Fits | Get file → | |
| Q5_K_M | 2.4 GB | 5.6 GB | Fits | Get file → | |
| Q6_K | 2.8 GB | 6.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2.06 GB, approx 5.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (2.41 GB, approx 5.6 GB). For 16 GB VRAM, Q6_K (2.79 GB, approx 6 GB). Smaller quants such as IQ1_S or IQ2_XXS are also available for tighter budgets.
What GPU do you need for Granite 4.0 H 3b Ar?
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 IQ1_S (0.8 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (2.8 GB file, about 6.0 GB in use).
Which Granite 4.0 H 3b Ar quant should you choose?
Q4_K_M is the usual starting point for Granite 4.0 H 3b Ar: it balances file size and quality well. Here it is a 2.1 GB file.
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 H 3b Ar
How much VRAM does Granite 4.0 H 3b Ar need?
About 5.2 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 H 3b Ar on an 8 GB GPU?
Yes, with Q6_K: the 2.8 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Granite 4.0 H 3b Ar GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.8 GB, IQ1_M is 0.9 GB, IQ2_XXS is 1.0 GB, IQ2_XS is 1.1 GB, IQ2_S is 1.1 GB and 19 more.
What context length does Granite 4.0 H 3b Ar 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 3b Ar GGUF?
The files are on Hugging Face in the mradermacher/granite-4.0-h-3b-ar-i1-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 3b Ar 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 3b Ar on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 5.2 GB of VRAM at 8k context, which fits within an 8 GB budget.
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.