Granite 4.0 350m Base needs about 1.7 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.2 GB (Q2_K) to 0.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Granite 4.0 350M Base – lightweight decoder‑only LLM
Granite 4.0 350M Base is a 0.352 billion‑parameter decoder‑only model. It supports 32 768‑token context and is trained on 15 trillion tokens. The model is available in multiple GGUF quantizations for efficient inference.
Good at
- Text summarization
- Question answering
- Code completion (FIM)
Limits
- No vision support
- License: Apache‑2.0
- Requires 8 k context for memory estimates
Best for
- Edge devices with limited VRAM
- Privacy‑preserving offline apps
- Baseline for fine‑tuning
Who it’s for. Developers building lightweight text generation tools on resource‑constrained hardware. The model is suitable for applications needing fast inference and low memory footprint while maintaining reasonable language capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.2 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_S | 0.2 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_M | 0.2 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_L | 0.2 GB | 1.7 GB | Fits | Get file → | |
| Q4_0 | 0.2 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 1.7 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 1.7 GB | Fits | Get file → | |
| Q4_1 | 0.2 GB | 1.7 GB | Fits | Get file → | |
| Q5_0 | 0.3 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_S | 0.3 GB | 1.7 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 1.7 GB | Fits | Get file → | |
| Q5_1 | 0.3 GB | 1.7 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 1.7 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.8 GB | Fits | Get file → | |
| BF16 | 0.7 GB | 2.1 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K or Q4_K_M (0.23 GB) are good choices, using about 1.7 GB RAM. If 4 GB VRAM is available, Q2_K (0.18 GB) or Q3_K_S (0.20 GB) provide the lowest memory usage. BF16 (0.71 GB) offers higher precision but needs more memory.
What GPU do you need for Granite 4.0 350m 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 BF16 (0.7 GB file, about 2.1 GB in use).
Which Granite 4.0 350m Base quant should you choose?
Q4_K_M is the usual starting point for Granite 4.0 350m Base: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.4 GB, about 1.6 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 0.2 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 350m Base
How much VRAM does Granite 4.0 350m Base need?
About 1.7 GB at Q4_K_M with an 8K context window. That is the 0.2 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 350m Base on an 8 GB GPU?
Yes, with BF16: the 0.7 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Granite 4.0 350m Base GGUF?
It depends on the quant: Q2_K is 0.2 GB, Q3_K_S is 0.2 GB, Q3_K_M is 0.2 GB, Q3_K_L is 0.2 GB, Q4_0 is 0.2 GB, Q4_K_S is 0.2 GB and 9 more.
What context length does Granite 4.0 350m Base support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Granite 4.0 350m Base GGUF?
The files are on Hugging Face in the ibm-granite/granite-4.0-350m-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 350m 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 350M Base on 8 GB VRAM?
Yes, using Q4_K or Q4_K_M quantizations requires about 1.7 GB VRAM and 1.7 GB RAM, well within 8 GB.
Does the model support image input?
No, Granite 4.0 350M Base is a text‑only model with no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.