Granite 3.2 8b Instruct Preview needs about 6.8 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 1.8 GB (IQ1_S) to 6.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Granite 3.2 8b Instruct Preview – 8B long‑context reasoning model
Granite 3.2 8b Instruct Preview is an 8B model with a 131072 token context window. It is fine‑tuned for enhanced reasoning and supports function‑calling and multilingual dialog. The model is released under Apache 2.0.
Good at
- Long‑context reasoning
- Multilingual dialog
- Function‑calling
Limits
- No vision support
- Requires 8k context for memory estimates
- No explicit language list beyond 12 languages
Best for
- AI assistants for business
- Long document summarization
- Code‑related tasks
Who it’s for. Developers building AI assistants or tools that need reasoning and multilingual support. The model is suitable for users who can run GGUF files with llama.cpp and have sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.8 GB | 3.7 GB | Fits | Get file → | |
| IQ1_M | 2.0 GB | 3.8 GB | Fits | Get file → | |
| IQ2_XXS | 2.3 GB | 4.1 GB | Fits | Get file → | |
| IQ2_XS | 2.5 GB | 4.3 GB | Fits | Get file → | |
| IQ2_S | 2.6 GB | 4.5 GB | Fits | Get file → | |
| IQ2_M | 2.8 GB | 4.7 GB | Fits | Get file → | |
| Q2_K_S | 2.9 GB | 4.7 GB | Fits | Get file → | |
| Q2_K | 3.1 GB | 4.9 GB | Fits | Get file → | |
| IQ3_XXS | 3.2 GB | 5.0 GB | Fits | Get file → | |
| IQ3_XS | 3.4 GB | 5.3 GB | Fits | Get file → | |
| Q3_K_S | 3.6 GB | 5.4 GB | Fits | Get file → | |
| IQ3_S | 3.6 GB | 5.5 GB | Fits | Get file → | |
| IQ3_M | 3.7 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_M | 4.0 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_L | 4.3 GB | 6.2 GB | Fits | Get file → | |
| IQ4_XS | 4.4 GB | 6.3 GB | Fits | Get file → | |
| Q4_0 | 4.7 GB | 6.5 GB | Fits | Get file → | |
| IQ4_NL | 4.7 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 4.7 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.8 GB | Fits | Get file → | |
| Q4_1 | 5.1 GB | 7.0 GB | Fits | Get file → | |
| Q5_K_S | 5.6 GB | 7.5 GB | Tight | Get file → | |
| Q5_K_M | 5.8 GB | 7.6 GB | Tight | Get file → | |
| Q6_K | 6.7 GB | 8.5 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (1.84 GB, 3.7 GB memory at 8k context) or IQ1_M (2 GB, 3.8 GB). If 12 GB VRAM is available, Q4_K_M (4.94 GB, 6.8 GB) or Q5_K_M (5.8 GB, 7.6 GB) provide higher quality. Larger models require 16 GB or more.
What GPU do you need for Granite 3.2 8b Instruct Preview?
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_M (2.0 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q3_K_M (4.0 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.8 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.5 GB in use).
Which Granite 3.2 8b Instruct Preview quant should you choose?
Q4_K_M is the usual starting point for Granite 3.2 8b Instruct Preview: it balances file size and quality well. Here it is a 4.9 GB file.
If memory is tight, the smallest file is IQ1_S at 1.8 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
Frequently asked questions about Granite 3.2 8b Instruct Preview
How much VRAM does Granite 3.2 8b Instruct Preview need?
About 6.8 GB at Q4_K_M with an 8K context window. That is the 4.9 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 3.2 8b Instruct Preview on an 8 GB GPU?
Yes, with Q5_K_M: the 5.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Granite 3.2 8b Instruct Preview GGUF?
It depends on the quant: IQ1_S is 1.8 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 18 more.
What context length does Granite 3.2 8b Instruct Preview support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Granite 3.2 8b Instruct Preview GGUF?
The files are on Hugging Face in the mradermacher/granite-3.2-8b-instruct-preview-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 3.2 8b Instruct Preview 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 this model on 8 GB VRAM?
Yes, use the IQ1_S or IQ1_M quant, which fit within 8 GB VRAM and use about 3.7–3.8 GB memory at 8k context.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache 2.0 license.