LU

Lucy

LucyGGUF by MenloUpdated 2025-08-04
Download on Hugging Face
Parameters1.72B
Context40K
Layers28
Architectureqwen3
Smallest quant0.9 GB
Quick answer

Lucy 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 13 quants, from 0.9 GB (Q3_K_S) to 1.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Lucy – a 1.7B Qwen3 model for mobile agentic web search

Lucy is a compact 1.7B model built on Qwen3-1.7B. It focuses on agentic web search and lightweight browsing, optimized for mobile devices and CPU‑only setups. The model uses machine‑generated task vectors and reinforcement learning to improve search reasoning.

Good at

  • Agentic web search with MCP tools
  • Lightweight browsing via Crawl4AI and Serper
  • Mobile‑friendly inference on CPU

Limits

  • No vision support
  • Requires 8k context for full performance
  • Apache‑2.0 license limits commercial use without attribution

Best for

  • Mobile agents needing quick web search
  • CPU‑only inference on low‑end hardware
  • Integrating search APIs into lightweight apps

Who it’s for. Developers building mobile or edge applications that require on‑device web search capabilities. The model is suitable for those who need a small footprint and can work within the 8k context limit.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S0.9 GB 2.3 GB
Fits Get file →
Q3_K_M0.9 GB 2.4 GB
Fits Get file →
Q3_K_L1.0 GB 2.4 GB
Fits Get file →
Q4_01.1 GB 2.5 GB
Fits Get file →
Q4_K_S1.1 GB 2.5 GB
Fits Get file →
Q4_K_M1.1 GB 2.5 GB
Fits Get file →
Q4_11.1 GB 2.6 GB
Fits Get file →
Q5_01.2 GB 2.7 GB
Fits Get file →
Q5_K_S1.2 GB 2.7 GB
Fits Get file →
Q5_K_M1.3 GB 2.7 GB
Fits Get file →
Q5_11.3 GB 2.8 GB
Fits Get file →
Q6_K1.4 GB 2.9 GB
Fits Get file →
Q8_01.8 GB 3.3 GB
Fits Get file →

For 8 GB VRAM, Q4_0 or Q4_K_S (1.05 GB, ~2.5 GB RAM) are suitable. With 4 GB VRAM, Q3_K_S (0.87 GB, ~2.3 GB RAM) fits. For 2 GB VRAM, Q3_K_S is the smallest option, but memory usage will be close to the limit.

What GPU do you need for Lucy?

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).

Which Lucy quant should you choose?

Q4_K_M is the usual starting point for Lucy: 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 Q3_K_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

Architectureqwen3
Parameters1.72B
Layers28
Trained context40,960 tokens
KV cache (fp16)112 KB per token

Source

Quantized byMenlo
FamilyLucy
Base modelMenlo/Lucy
RepositoryMenlo/Lucy-gguf
Licenseapache-2.0
Downloads (HF)459
Last updated2025-08-04

Frequently asked questions about Lucy

How much VRAM does Lucy 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 on an 8 GB GPU?

Yes, with Q8_0: the 1.8 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Lucy GGUF?

It depends on the quant: Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, Q4_0 is 1.1 GB, Q4_K_S is 1.1 GB, Q4_K_M is 1.1 GB and 7 more.

What context length does Lucy support?

The GGUF header lists a trained context length of 40,960 tokens (40K). 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 GGUF?

The files are on Hugging Face in the Menlo/Lucy-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 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 on 8 GB VRAM?

Yes, Q4_0 or Q4_K_S quantizations fit within 8 GB VRAM and use about 2.5 GB RAM at 8k context.

Does Lucy support vision tasks?

No, Lucy does not have vision capabilities.

What context length does Lucy require?

Lucy was trained with 40960 tokens and performs best with 8k context length.

Other GGUFs of Lucy

Similar models

Browse all →

More from Menlo

All by Menlo →

More Lucy models

All Lucy →

Other tiny models

All tiny models →