QW

LocateAnything-3B

QwenGGUF by MungertUpdated 2026-06-06
Download on Hugging Face
Parameters3.4B
Context32K
Layers36
Architectureqwen2
Smallest quant0.0 GB
Quick answer

LocateAnything-3B needs about 3.2 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 6.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

LocateAnything-3B: 3.4B Qwen2.5 instruction model with vision and tools

LocateAnything-3B is a 3.4B parameter Qwen2.5 model fine‑tuned for instruction following, vision, and tool use. It supports a full 32,768 token context and can generate up to 8,192 tokens. The model is available in multiple GGUF quantizations.

Good at

  • Vision‑language tasks
  • Tool invocation
  • Long‑context generation

Limits

  • No vision support in some quantizations
  • Requires 8,192 token context for full generation
  • License type is other

Best for

  • Image captioning
  • Interactive chatbot with tool calls
  • Document summarization

Who it’s for. Developers building vision‑enabled assistants or tools that need instruction‑following capabilities. The model is suitable for applications that can handle a 32,768 token context and require a balance of language and vision performance.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.8 GB
Fits Get file →
IQ2_XS1.3 GB 2.1 GB
Fits Get file →
IQ2_S1.3 GB 2.1 GB
Fits Get file →
IQ2_M1.4 GB 2.2 GB
Fits Get file →
Q2_K_S1.4 GB 2.2 GB
Fits Get file →
Q2_K_M1.5 GB 2.3 GB
Fits Get file →
IQ3_XXS1.6 GB 2.4 GB
Fits Get file →
IQ3_XS1.6 GB 2.5 GB
Fits Get file →
IQ3_M1.8 GB 2.6 GB
Fits Get file →
Q3_K_S1.8 GB 2.6 GB
Fits Get file →
Q3_K_M1.9 GB 2.7 GB
Fits Get file →
IQ4_NL1.9 GB 2.7 GB
Fits Get file →
IQ4_XS2.0 GB 2.8 GB
Fits Get file →
Q4_K_S2.2 GB 3.0 GB
Fits Get file →
Q4_12.2 GB 3.0 GB
Fits Get file →
Q4_02.2 GB 3.0 GB
Fits Get file →
Q4_K_M2.4 GB 3.2 GB
Fits Get file →
Q5_02.6 GB 3.4 GB
Fits Get file →
Q5_K_M2.7 GB 3.5 GB
Fits Get file →
Q5_12.8 GB 3.6 GB
Fits Get file →
Q6_K_M2.9 GB 3.7 GB
Fits Get file →
Q8_03.6 GB 4.4 GB
Fits Get file →
BF165.1 GB 5.9 GB
Fits Get file →
F165.1 GB 5.9 GB
Fits Get file →
BF166.8 GB 7.6 GB
Tight Get file →

For 8 GB VRAM, use Q4_K_M (2.38 GB file, ~3.2 GB memory at 8k context). For 4 GB VRAM, use IQ2_XS (1.26 GB file, ~2.1 GB memory). For higher precision, choose Q8_0 (3.62 GB file, ~4.4 GB memory).

What GPU do you need for LocateAnything-3B?

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 Q6_K_M (2.9 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (5.1 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (6.8 GB file, about 7.6 GB in use).

Which LocateAnything-3B quant should you choose?

Q4_K_M is the usual starting point for LocateAnything-3B: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 3.6 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 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

Architectureqwen2
Parameters3.4B
Layers36
Trained context32,768 tokens
KV cache (fp16)36 KB per token

Source

Quantized byMungert
FamilyQwen
Licenseother
Downloads (HF)877
Last updated2026-06-06

Frequently asked questions about LocateAnything-3B

How much VRAM does LocateAnything-3B need?

About 3.2 GB at Q4_K_M with an 8K context window. That is the 2.4 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 LocateAnything-3B on an 8 GB GPU?

Yes, with BF16: the 6.8 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of LocateAnything-3B GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XS is 1.3 GB, IQ2_S is 1.3 GB, IQ2_M is 1.4 GB, Q2_K_S is 1.4 GB, Q2_K_M is 1.5 GB and 19 more.

What context length does LocateAnything-3B support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download LocateAnything-3B GGUF?

The files are on Hugging Face in the Mungert/LocateAnything-3B-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 LocateAnything-3B use?

Hugging Face lists the license as other. 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 LocateAnything-3B on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 3.2 GB of VRAM at 8k context, which fits within 8 GB.

Does the model support vision tasks?

Yes, the model has detected vision ability, but some quantizations may not include full vision support.

What is the maximum context length?

The model supports a full 32,768 token context and can generate up to 8,192 tokens.

Other GGUFs of Qwen2.5-3B-Instruct

Similar models

Browse all →

More from Mungert

All by Mungert →

More Qwen models

All Qwen →

Other tiny models

All tiny models →