AREX Turbo needs about 4.5 GB of memory at Q4_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 8.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
AREX Turbo – a 4.2B dense research agent with 262k token context
AREX Turbo is a 4.2B parameter dense model built on Qwen3.5-4B. It supports long‑horizon reasoning, tool use, and vision. The model retains the recursive self‑improvement framework of the AREX family, enabling verification‑guided research and autonomous context updates.
Good at
- Long‑horizon reasoning
- Tool‑driven research
- Vision integration
Limits
- Large context requires high VRAM
- No external vision API support
- Apache‑2.0 license limits commercial use
Best for
- Research‑oriented chatbots
- Automated evidence gathering
- Multi‑step problem solving
Who it’s for. Developers building research agents or advanced chat systems that need deep reasoning and verification. Suitable for teams that can host the model locally and manage its context updates.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ2_M | 1.8 GB | 3.4 GB | Fits | Get file → | |
| Q2_K | 2.1 GB | 3.6 GB | Fits | Get file → | |
| IQ3_XXS | 2.1 GB | 3.7 GB | Fits | Get file → | |
| Q2_K_L | 2.2 GB | 3.8 GB | Fits | Get file → | |
| IQ3_XS | 2.3 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_S | 2.3 GB | 3.9 GB | Fits | Get file → | |
| IQ3_M | 2.4 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_M | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_L | 2.5 GB | 4.1 GB | Fits | Get file → | |
| IQ4_XS | 2.5 GB | 4.1 GB | Fits | Get file → | |
| IQ4_NL | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q4_0 | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q3_K_XL | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_S | 2.7 GB | 4.3 GB | Fits | Get file → | |
| Q4_1 | 2.9 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_M | 2.9 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_L | 3.0 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_S | 3.1 GB | 4.7 GB | Fits | Get file → | |
| Q5_K_M | 3.3 GB | 4.9 GB | Fits | Get file → | |
| Q5_K_L | 3.5 GB | 5.0 GB | Fits | Get file → | |
| Q6_K | 3.7 GB | 5.3 GB | Fits | Get file → | |
| Q6_K_L | 3.8 GB | 5.4 GB | Fits | Get file → | |
| Q8_0 | 4.5 GB | 6.1 GB | Fits | Get file → | |
| BF16 | 8.4 GB | 10.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (≈4.5 GB memory at 8k context). With 12 GB VRAM, Q5_K_M (≈4.9 GB) or Q6_K (≈5.3 GB) offer higher quality. For 16 GB VRAM, Q6_K_L (≈5.4 GB) or Q8_0 (≈6.1 GB) provide the best trade‑off between size and performance.
What GPU do you need for AREX Turbo?
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 Q3_K_M (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K_L (3.8 GB file, about 5.4 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.5 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.4 GB file, about 10.0 GB in use).
Which AREX Turbo quant should you choose?
Q4_K_M is the usual starting point for AREX Turbo: it balances file size and quality well. Here it is a 2.9 GB file.
The Q8_0 file is 4.5 GB, about 1.6 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about AREX Turbo
How much VRAM does AREX Turbo need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 2.9 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 AREX Turbo on an 8 GB GPU?
Yes, with Q8_0: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of AREX Turbo GGUF?
It depends on the quant: file is 0.0 GB, IQ2_M is 1.8 GB, Q2_K is 2.1 GB, IQ3_XXS is 2.1 GB, Q2_K_L is 2.2 GB, IQ3_XS is 2.3 GB and 19 more.
What context length does AREX Turbo support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download AREX Turbo GGUF?
The files are on Hugging Face in the bartowski/BAAI_AREX-Turbo-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 AREX Turbo 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 AREX Turbo on 8 GB VRAM?
Yes, a Q4_K_M quantized file uses about 4.5 GB of VRAM at 8k context, which fits in 8 GB. Higher quants will exceed the limit.
Does AREX Turbo support vision tasks?
Yes, the model detects vision ability, but it requires external image‑to‑text processing; no built‑in vision API is included.
What license applies to AREX Turbo?
The model is released under the Apache‑2.0 license, allowing free use with attribution and no commercial restrictions.