Loopl 2b needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.0 GB (Q2_K) to 3.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Loopl 2B – a 1.88B Qwen3.5 agent model with vision support
Loopl 2B is a 1.88B parameter Qwen3.5 model tuned for on‑device agent use. It includes a frozen vision tower and supports reasoning, tool use, and image understanding. The model runs on the phone or local runtimes such as llama.cpp and MLX.
Good at
- reasoning
- tools
- vision
Limits
- trained context 262144 tokens
- requires 8k context memory estimates 1.9–4.7 GB
- licensed under apache‑2.0
Best for
- on‑device agent interactions
- offline tool execution
- image analysis on mobile
Who it’s for. Developers building lightweight on‑device agents and iPhone users who want an offline AI that can reason, use tools, and read images without a server.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_L | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ4_XS | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q5_K_S | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 2.5 GB | Fits | Get file → | |
| Q8_0 | 2.0 GB | 2.9 GB | Fits | Get file → | |
| F16 | 3.8 GB | 4.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 1.27 GB, estimated 2.2 GB memory). For 6 GB VRAM, Q3_K_M (1.1 GB, 2 GB memory) is suitable. For 4 GB VRAM, Q2_K (0.97 GB, 1.9 GB memory) fits best. All estimates are approximate.
What GPU do you need for Loopl 2b?
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 (2.0 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.8 GB file, about 4.7 GB in use).
Which Loopl 2b quant should you choose?
Q4_K_M is the usual starting point for Loopl 2b: it balances file size and quality well. Here it is a 1.3 GB file.
The Q8_0 file is 2.0 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 Q2_K at 1.0 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 Loopl 2b
How much VRAM does Loopl 2b need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Loopl 2b on an 8 GB GPU?
Yes, with F16: the 3.8 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Loopl 2b GGUF?
It depends on the quant: Q2_K is 1.0 GB, Q3_K_S is 1.0 GB, Q3_K_M is 1.1 GB, Q3_K_L is 1.2 GB, IQ4_XS is 1.2 GB, Q4_K_S is 1.2 GB and 6 more.
What context length does Loopl 2b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download Loopl 2b GGUF?
The files are on Hugging Face in the mradermacher/loopl-2b-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 Loopl 2b 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 Loopl 2B on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 2.2 GB of VRAM at 8k context, which fits in 8 GB.
Does Loopl 2B support vision?
Yes, the model includes a frozen vision tower and the iPhone app shows a photo button.