Aira-2-1B5 needs about 4.2 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 15 quants, from 0.9 GB (IQ3_S) to 3.3 GB (F16).
Instruction‑tuned GPT‑2 model with 1.64B parameters
Aira‑2‑1B5 is an instruction‑tuned GPT‑2 model trained on synthetic prompts and completions. It contains 1,557,614,400 parameters and supports English language generation. The model is released under Apache‑2.0 license.
Good at
- Instruction following
- Short‑form dialogue
- English text generation
Limits
- Context limited to 1024 tokens
- May hallucinate or produce toxic content
- No vision or multimodal support
Best for
- Chatbot prototypes
- Rapid prototyping of instruction‑based LLMs
- Educational demonstrations
Who it’s for. Developers and researchers looking for a lightweight, instruction‑tuned GPT‑2 variant. The model is suitable for environments with limited GPU memory and for projects that require an open‑source, permissively licensed LLM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_S | 0.9 GB | 1.7 GB | Fits | Get file → | |
| IQ3_XS | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q2_K | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 1.7 GB | Fits | Get file → | |
| IQ4_XS | 1.0 GB | 1.8 GB | Fits | Get file → | |
| IQ3_M | 1.0 GB | 1.8 GB | Fits | Get file → | |
| Q3_K_M | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_L | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q4_K_M | 1.2 GB | 2.0 GB | Fits | Get file → | |
| Q5_K_S | 1.2 GB | 2.0 GB | Fits | Get file → | |
| Q5_K_M | 1.4 GB | 2.2 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 2.4 GB | Fits | Get file → | |
| Q8_0 | 1.7 GB | 2.6 GB | Fits | Get file → | |
| F16 | 3.3 GB | 4.1 GB | Fits | Get file → |
For 8 GB VRAM, use IQ3_S or IQ3_XS (0.91 GB, ~3.9 GB RAM). For 12 GB VRAM, IQ4_XS (0.97 GB, ~4 GB RAM) or Q3_K_M (1.04 GB, ~4.1 GB RAM). For 16 GB VRAM, Q4_K_M (1.19 GB, ~4.2 GB RAM) or Q5_K_M (1.38 GB, ~4.4 GB RAM). Estimates are approximate.
What GPU do you need for Aira-2-1B5?
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 IQ3_M (1.0 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (1.7 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (3.3 GB file, about 6.3 GB in use).
Which Aira-2-1B5 quant should you choose?
Q4_K_M is the usual starting point for Aira-2-1B5: it balances file size and quality well. Here it is a 1.2 GB file.
The Q8_0 file is 1.7 GB, about 1.5 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_S at 0.9 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 Aira-2-1B5
How much VRAM does Aira-2-1B5 need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.2 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 Aira-2-1B5 on an 8 GB GPU?
Yes, with F16: the 3.3 GB file needs about 6.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Aira-2-1B5 GGUF?
It depends on the quant: IQ3_S is 0.9 GB, IQ3_XS is 0.9 GB, Q2_K is 0.9 GB, Q3_K_S is 0.9 GB, IQ4_XS is 1.0 GB, IQ3_M is 1.0 GB and 9 more.
What context length does Aira-2-1B5 support?
The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 2.5 GB at 8K and 0.3 GB at 1K.
Where can I download Aira-2-1B5 GGUF?
The files are on Hugging Face in the mradermacher/Aira-2-1B5-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-2-1B5 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 Aira‑2‑1B5 on 8 GB VRAM?
Yes, use IQ3_S or IQ3_XS quantizations; they require about 3.9 GB VRAM at 8K context.
Does the model support multiple languages?
The training data is English only; no other languages are supported.
Is the model free to use?
Yes, it is licensed under Apache‑2.0, allowing free use and modification.