Aira 2 Portuguese 560M needs about 1.9 GB of memory at Q4_K_M (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 0.3 GB (IQ1_S) to 0.7 GB (Q6_K).
Aira 2 Portuguese 560M – instruction‑tuned BLOOM model in Portuguese
Aira‑2 Portuguese 560M is a 0.816 billion‑parameter BLOOM model trained on synthetic prompts and completions. It is instruction‑tuned for Portuguese and supports up to 1 024 context tokens.
Good at
- Instruction following in Portuguese
- Short‑form Q&A
- Conversational prompts
Limits
- Hallucinations possible
- Biases and toxicity may appear
- No vision support
Best for
- Chatbot prototypes
- Portuguese FAQ systems
- Lightweight local inference
Who it’s for. Developers building Portuguese‑language assistants who need a small, instruction‑tuned model. Researchers testing BLOOM variants on local hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ1_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ2_XXS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ2_XS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ2_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ2_M | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q2_K_S | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ3_XXS | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q2_K | 0.4 GB | 1.0 GB | Fits | Get file → | |
| IQ3_XS | 0.5 GB | 1.1 GB | Fits | Get file → | |
| IQ3_S | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q3_K_S | 0.5 GB | 1.1 GB | Fits | Get file → | |
| IQ3_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q3_K_L | 0.5 GB | 1.1 GB | Fits | Get file → | |
| IQ4_XS | 0.5 GB | 1.1 GB | Fits | Get file → | |
| IQ4_NL | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q4_0 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_S | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q4_K_M | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q4_1 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q5_K_S | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.2 GB | Fits | Get file → | |
| Q6_K | 0.7 GB | 1.3 GB | Fits | Get file → |
For 8 GB VRAM, use IQ1_S or IQ1_M (0.34 GB file, ~1.6 GB memory). For 12 GB VRAM, IQ2_S or Q4_K_M (0.39–0.56 GB file, ~1.7–1.9 GB memory). For 16 GB VRAM, Q5_K_M or Q6_K (0.63–0.68 GB file, ~1.9–2 GB memory).
What GPU do you need for Aira 2 Portuguese 560M?
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 (0.7 GB file, about 2.0 GB in use).
Which Aira 2 Portuguese 560M quant should you choose?
Q4_K_M is the usual starting point for Aira 2 Portuguese 560M: it balances file size and quality well. Here it is a 0.6 GB file.
If memory is tight, the smallest file is IQ1_S at 0.3 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 Aira 2 Portuguese 560M
How much VRAM does Aira 2 Portuguese 560M need?
About 1.9 GB at Q4_K_M with an 8K context window. That is the 0.6 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 Aira 2 Portuguese 560M on an 8 GB GPU?
Yes, with Q6_K: the 0.7 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Aira 2 Portuguese 560M GGUF?
It depends on the quant: IQ1_S is 0.3 GB, IQ1_M is 0.3 GB, IQ2_XXS is 0.4 GB, IQ2_XS is 0.4 GB, IQ2_S is 0.4 GB, IQ2_M is 0.4 GB and 18 more.
What context length does Aira 2 Portuguese 560M support?
The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.1 GB at 1K.
Where can I download Aira 2 Portuguese 560M GGUF?
The files are on Hugging Face in the mradermacher/Aira-2-portuguese-560M-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 Aira 2 Portuguese 560M use?
Hugging Face lists the license as bigscience-bloom-rail-1.0. 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, IQ1_S or IQ1_M quantizations fit within 8 GB VRAM, using about 1.6 GB of memory at 8 k context.
Does it support English?
The model is trained for Portuguese; English support is limited and may produce less accurate responses.
Is there a license restriction?
It is licensed under bigscience‑bloom‑rail‑1.0, which allows research and commercial use with attribution.