Granite 4.0 H 1b Base needs about 3.4 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.6 GB (Q2_K) to 2.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
Granite 4.0 H 1b Base – lightweight decoder‑only LLM
Granite 4.0 H 1b Base is a 1.46B parameter decoder‑only model optimized for efficiency. It supports Fill‑in‑the‑Middle code completion and runs on resource‑constrained devices. The model is trained on 15 trillion tokens and released under Apache 2.0.
Good at
- Text summarization
- Question answering
- Code completion (FIM)
Limits
- No vision support
- Requires 8k context for estimates
- License is Apache 2.0
Best for
- Offline text generation
- Privacy‑preserving chatbots
- Embedded code editors
Who it’s for. Developers needing a small, fast language model for mobile or IoT applications. Researchers can fine‑tune it for additional languages or specialized tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.6 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_S | 0.7 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_M | 0.7 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_L | 0.8 GB | 3.3 GB | Fits | Get file → | |
| Q4_0 | 0.9 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_S | 0.9 GB | 3.4 GB | Fits | Get file → | |
| Q4_K_M | 0.9 GB | 3.4 GB | Fits | Get file → | |
| Q4_1 | 0.9 GB | 3.5 GB | Fits | Get file → | |
| Q5_0 | 1.0 GB | 3.5 GB | Fits | Get file → | |
| Q5_K_S | 1.0 GB | 3.5 GB | Fits | Get file → | |
| Q5_K_M | 1.0 GB | 3.6 GB | Fits | Get file → | |
| Q5_1 | 1.1 GB | 3.6 GB | Fits | Get file → | |
| Q6_K | 1.2 GB | 3.7 GB | Fits | Get file → | |
| Q8_0 | 1.6 GB | 4.1 GB | Fits | Get file → | |
| BF16 | 2.9 GB | 5.4 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M or Q4_K_S (≈0.9 GB) provide a good balance of speed and quality. If memory is tighter, Q3_K_M (≈0.73 GB) is suitable. For maximum quality within 10 GB, use Q5_K_M (≈1.05 GB).
What GPU do you need for Granite 4.0 H 1b Base?
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 Q6_K (1.2 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (2.9 GB file, about 5.4 GB in use).
Which Granite 4.0 H 1b Base quant should you choose?
Q4_K_M is the usual starting point for Granite 4.0 H 1b Base: it balances file size and quality well. Here it is a 0.9 GB file.
The Q8_0 file is 1.6 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 Q2_K at 0.6 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 1b Base
How much VRAM does Granite 4.0 H 1b Base need?
About 3.4 GB at Q4_K_M with an 8K context window. That is the 0.9 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 1b Base on an 8 GB GPU?
Yes, with BF16: the 2.9 GB file needs about 5.4 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 1b Base GGUF?
It depends on the quant: Q2_K is 0.6 GB, Q3_K_S is 0.7 GB, Q3_K_M is 0.7 GB, Q3_K_L is 0.8 GB, Q4_0 is 0.9 GB, Q4_K_S is 0.9 GB and 9 more.
What context length does Granite 4.0 H 1b Base 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 H 1b Base GGUF?
The files are on Hugging Face in the ibm-granite/granite-4.0-h-1b-base-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 1b Base 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 1b Base on 8 GB VRAM?
Yes, use a Q4_K quantization which requires about 3.4 GB of VRAM at 8k context.
Does the model support image inputs?
No, Granite 4.0 H 1b Base is a text‑only decoder model.
What license does the model use?
The model is released under the Apache 2.0 license.