Loopl 0.8b needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.4 GB (Q2_K) to 1.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Loopl 0.8b – a small Qwen3.5‑based agent with vision
Loopl 0.8b is a 0.752 billion‑parameter Qwen3.5 model fine‑tuned for on‑device agent use. It supports reasoning, tools, and vision, and is distributed as GGUF files for llama.cpp and MLX. The model is licensed under Apache‑2.0.
Good at
- On‑device reasoning
- Tool‑driven interactions
- Image reading
Limits
- No external vision tower beyond the frozen base
- Requires 8 k context for estimates
- No GPU‑specific optimisations listed
Best for
- Mobile chatbot apps
- Offline tool‑based assistants
- Vision‑enabled local queries
Who it’s for. Developers building lightweight on‑device agents that need reasoning, tool use, and basic image understanding. The model is ideal for iPhone or Mac users who want a private, no‑account solution.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q3_K_S | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_L | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ4_XS | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q5_K_S | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → | |
| F16 | 1.5 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (0.53 GB, ~1.4 GB memory) or Q5_K_S (0.56 GB, ~1.5 GB memory) are suitable. If memory is tighter, Q3_K_M (0.47 GB, ~1.4 GB memory) or Q2_K (0.42 GB, ~1.3 GB memory) can be used. For the highest fidelity, use Q8_0 (0.81 GB, ~1.7 GB memory).
What GPU do you need for Loopl 0.8b?
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 F16 (1.5 GB file, about 2.4 GB in use).
Which Loopl 0.8b quant should you choose?
Q4_K_M is the usual starting point for Loopl 0.8b: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.8 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 Q2_K at 0.4 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 0.8b
How much VRAM does Loopl 0.8b need?
About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 0.8b on an 8 GB GPU?
Yes, with F16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Loopl 0.8b GGUF?
It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, Q4_K_S is 0.5 GB, IQ4_XS is 0.5 GB and 6 more.
What context length does Loopl 0.8b 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 0.8b GGUF?
The files are on Hugging Face in the mradermacher/loopl-0.8b-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 0.8b 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 0.8b on 8 GB VRAM with Q4_K_M?
Yes, Q4_K_M uses about 1.4 GB of VRAM at 8 k context, well within an 8 GB budget.
Does Loopl support vision on Mac with MLX?
Yes, the base vision tower is frozen and included in the MLX export, enabling photo analysis on Mac.
Is the model licensed for commercial use?
The model is released under Apache‑2.0, which permits commercial use with attribution.