Lucy 128k needs about 2.5 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 23 quants, from 0.8 GB (IQ3_XXS) to 3.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Lucy 128k – a 1.72B Qwen3 model for agentic web search on mobile
Lucy 128k is a 1.72B parameter model built on Qwen3. It focuses on agentic web search and lightweight browsing, optimized for mobile devices and CPU-only setups. The model supports MCP-enabled tools such as Serper and Crawl4AI.
Good at
- Agentic web search
- Lightweight mobile inference
- CPU‑only deployment
Limits
- No vision support
- Limited context to 131072 tokens
- Apache‑2.0 license
Best for
- Mobile web‑search assistants
- Lightweight browsing bots
- CPU‑only inference on edge devices
Who it’s for. Developers building mobile or edge‑device assistants that need web‑search capabilities without heavy GPU resources. The model is suitable for projects requiring a small footprint and efficient CPU inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 0.8 GB | 2.2 GB | Fits | Get file → | |
| Q2_K | 0.8 GB | 2.2 GB | Fits | Get file → | |
| IQ3_XS | 0.8 GB | 2.3 GB | Fits | Get file → | |
| Q2_K_L | 0.9 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 2.3 GB | Fits | Get file → | |
| IQ3_M | 0.9 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.0 GB | 2.4 GB | Fits | Get file → | |
| IQ4_XS | 1.0 GB | 2.4 GB | Fits | Get file → | |
| IQ4_NL | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_0 | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q3_K_XL | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_1 | 1.1 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_L | 1.2 GB | 2.6 GB | Fits | Get file → | |
| Q5_K_S | 1.2 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_L | 1.3 GB | 2.8 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 2.9 GB | Fits | Get file → | |
| Q6_K_L | 1.5 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 3.3 GB | Fits | Get file → | |
| BF16 | 3.4 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M or Q4_K_L (file size 1.11 GB or 1.18 GB, memory ~2.5–2.6 GB). For 4 GB VRAM, choose Q2_K or IQ3_XXS (file size 0.78 GB or 0.75 GB, memory ~2.2 GB). For 2 GB VRAM, use IQ3_XXS or Q2_K (file size 0.75 GB or 0.78 GB, memory ~2.2 GB).
What GPU do you need for Lucy 128k?
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 (1.8 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.4 GB file, about 4.9 GB in use).
Which Lucy 128k quant should you choose?
Q4_K_M is the usual starting point for Lucy 128k: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.8 GB, about 1.7 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_XXS at 0.8 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 Lucy 128k
How much VRAM does Lucy 128k need?
About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Lucy 128k on an 8 GB GPU?
Yes, with BF16: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Lucy 128k GGUF?
It depends on the quant: IQ3_XXS is 0.8 GB, Q2_K is 0.8 GB, IQ3_XS is 0.8 GB, Q2_K_L is 0.9 GB, Q3_K_S is 0.9 GB, IQ3_M is 0.9 GB and 17 more.
What context length does Lucy 128k support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Lucy 128k GGUF?
The files are on Hugging Face in the bartowski/Menlo_Lucy-128k-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 Lucy 128k 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 Lucy 128k on 8 GB VRAM?
Yes, quantizations such as Q4_K_M or Q4_K_L fit within 8 GB VRAM and use about 2.5–2.6 GB of memory at 8 k context.
Does Lucy 128k support vision?
No, the model has no vision capabilities and is focused solely on text and web‑search tasks.