Granite 3b Code Base needs about 5.3 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 22 quants, from 1.3 GB (Q2_K) to 3.7 GB (Q8_0).
Granite 3b Code Base – a 3.48B parameter code generation model
Granite 3b Code Base is a 3.48B parameter llama architecture model focused on coding tasks. It was trained on code datasets such as codeparrot/github-code-clean and bigcode/starcoderdata. The model is released under the apache-2.0 license.
Good at
- Code generation
- Python and JavaScript support
- Small context size 2048 tokens
Limits
- No vision support
- Limited to 2048 token context
- Requires at least 4.5 GB VRAM for Q2_K
Best for
- Writing boilerplate code
- Debugging snippets
- Learning programming patterns
Who it’s for. Developers and researchers needing a lightweight code generation model. The model is suitable for local inference on machines with moderate GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.3 GB | 2.5 GB | Fits | Get file → | |
| IQ3_XS | 1.5 GB | 2.6 GB | Fits | Get file → | |
| IQ3_S | 1.6 GB | 2.7 GB | Fits | Get file → | |
| Q3_K_S | 1.6 GB | 2.7 GB | Fits | Get file → | |
| IQ3_M | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q3_K | 1.7 GB | 2.9 GB | Fits | Get file → | |
| Q3_K_M | 1.7 GB | 2.9 GB | Fits | Get file → | |
| Q3_K_L | 1.9 GB | 3.0 GB | Fits | Get file → | |
| IQ4_XS | 1.9 GB | 3.1 GB | Fits | Get file → | |
| Q4_0 | 2.0 GB | 3.2 GB | Fits | Get file → | |
| IQ4_NL | 2.0 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_S | 2.0 GB | 3.2 GB | Fits | Get file → | |
| Q4_K | 2.1 GB | 3.3 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 3.3 GB | Fits | Get file → | |
| Q4_1 | 2.2 GB | 3.4 GB | Fits | Get file → | |
| Q5_0 | 2.4 GB | 3.6 GB | Fits | Get file → | |
| Q5_K_S | 2.4 GB | 3.6 GB | Fits | Get file → | |
| Q5_K | 2.5 GB | 3.7 GB | Fits | Get file → | |
| Q5_K_M | 2.5 GB | 3.7 GB | Fits | Get file → | |
| Q5_1 | 2.6 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.9 GB | 4.0 GB | Fits | Get file → | |
| Q8_0 | 3.7 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM use Q2_K (1.34 GB file, 4.5 GB memory). For 12 GB VRAM use Q4_K (2.13 GB file, 5.3 GB memory). Higher quality quants such as Q5_K require 5.7 GB memory and 2.49 GB file size.
What GPU do you need for Granite 3b Code 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q6_K (2.9 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 6.9 GB in use).
Which Granite 3b Code Base quant should you choose?
Q4_K_M is the usual starting point for Granite 3b Code Base: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.7 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 1.3 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 3b Code Base
How much VRAM does Granite 3b Code Base need?
About 5.3 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 3b Code Base on an 8 GB GPU?
Yes, with Q8_0: the 3.7 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Granite 3b Code Base GGUF?
It depends on the quant: Q2_K is 1.3 GB, IQ3_XS is 1.5 GB, IQ3_S is 1.6 GB, Q3_K_S is 1.6 GB, IQ3_M is 1.6 GB, Q3_K is 1.7 GB and 16 more.
What context length does Granite 3b Code Base support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.
Where can I download Granite 3b Code Base GGUF?
The files are on Hugging Face in the RichardErkhov/ibm-granite_-_granite-3b-code-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 3b Code 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 3b Code Base on 8 GB VRAM?
Yes, the Q2_K quant uses 4.5 GB memory at 8k context, fitting within 8 GB VRAM.
Does this model support image input?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache-2.0 license.