granite-3.0-2b-instruct needs about 2.8 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 21 quants, from 1.1 GB (IQ3_XXS) to 5.3 GB (BF16).
Granite‑3.0‑2B‑Instruct: 2.63B‑parameter instruction‑tuned model
Granite‑3.0‑2B‑Instruct is a 2.63B‑parameter decoder‑only model finetuned from Granite‑3.0‑2B‑Base. It supports instruction following and tool usage. The model was released on October 21st, 2024 under Apache‑2.0.
Good at
- Instruction following
- Tool usage
- Text generation
Limits
- No vision support
- Limited to 4096 context tokens
- Requires Apache‑2.0 license
Best for
- Chat‑style instruction tasks
- Tool‑enabled workflows
- Text generation in supported languages
Who it’s for. Developers and researchers needing a lightweight instruction‑tuned model for text‑to‑text tasks. The model is suitable for applications that require structured chat interactions and tool integration.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 1.1 GB | 2.0 GB | Fits | Get file → | |
| IQ3_XS | 1.1 GB | 2.0 GB | Fits | Get file → | |
| IQ3_M | 1.3 GB | 2.1 GB | Fits | Get file → | |
| IQ3_S | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_S | 1.3 GB | 2.1 GB | Fits | Get file → | |
| Q3_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| IQ4_XS | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q4_0 | 1.5 GB | 2.3 GB | Fits | Get file → | |
| IQ4_NL | 1.5 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_S | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q4_1 | 1.6 GB | 2.5 GB | Fits | Get file → | |
| Q5_0 | 1.8 GB | 2.6 GB | Fits | Get file → | |
| Q5_K_S | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q5_1 | 2.0 GB | 2.8 GB | Fits | Get file → | |
| Q6_K_M | 2.2 GB | 3.0 GB | Fits | Get file → | |
| Q8_0 | 2.8 GB | 3.6 GB | Fits | Get file → | |
| BF16 | 3.8 GB | 4.7 GB | Fits | Get file → | |
| F16 | 3.8 GB | 4.7 GB | Fits | Get file → | |
| BF16 | 5.3 GB | 6.1 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 1.61 GB, memory 2.8 GB at 8k context). For 12 GB VRAM, Q5_K_M (1.89 GB, 3.1 GB). For 24 GB VRAM, Q8_0 (2.8 GB, 4 GB).
What GPU do you need for granite-3.0-2b-instruct?
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 Q8_0 (2.8 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.8 GB file, about 5.0 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.3 GB file, about 6.4 GB in use).
Which granite-3.0-2b-instruct quant should you choose?
Q4_K_M is the usual starting point for granite-3.0-2b-instruct: it balances file size and quality well. Here it is a 1.6 GB file.
The Q8_0 file is 2.8 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 IQ3_XXS at 1.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about granite-3.0-2b-instruct
How much VRAM does granite-3.0-2b-instruct need?
About 2.8 GB at Q4_K_M with an 8K context window. That is the 1.6 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-3.0-2b-instruct on an 8 GB GPU?
Yes, with BF16: the 5.3 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of granite-3.0-2b-instruct GGUF?
It depends on the quant: IQ3_XXS is 1.1 GB, IQ3_XS is 1.1 GB, IQ3_M is 1.3 GB, IQ3_S is 1.3 GB, Q3_K_S is 1.3 GB, Q3_K_M is 1.3 GB and 15 more.
What context length does granite-3.0-2b-instruct support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.7 GB at 8K and 0.3 GB at 4K.
Where can I download granite-3.0-2b-instruct GGUF?
The files are on Hugging Face in the Mungert/granite-3.0-2b-instruct-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-3.0-2b-instruct 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‑3.0‑2B‑Instruct on 8 GB VRAM?
Yes, using the Q4_K_M quantized file (1.61 GB) which requires about 2.8 GB of VRAM at 8k context.
Does the model support image inputs?
No, Granite‑3.0‑2B‑Instruct does not support vision or multimodal inputs.
What license applies to this model?
The model is released under the Apache‑2.0 license.