QW

Fathom-Search-4B

QwenGGUF by MungertUpdated 2025-10-23
Download on Hugging Face
Parameters4B
Context40K
Layers36
Architectureqwen3
Smallest quant0.0 GB
Quick answer

Fathom-Search-4B needs about 4.3 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 8.1 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Fathom-Search-4B – a 4B‑parameter Qwen3 model optimized for long‑horizon search tasks

Fathom-Search-4B is a 4.0B‑parameter Qwen3 model tailored for evidence‑seeking and long‑horizon information retrieval. It supports a native context length of 32,768 tokens and can be extended to 131,072 tokens with YaRN. The model is released under the MIT license.

Good at

  • Long‑horizon search and retrieval
  • Evidence‑seeking dialogue
  • Agentic task integration

Limits

  • No vision support
  • Requires 8,000‑token context for memory estimates
  • No mixture‑of‑experts

Best for

  • Search‑driven chatbots
  • Research assistants needing long context
  • Agentic workflows with external tools

Who it’s for. Developers building search‑centric LLM applications or research assistants that need to retrieve and synthesize information over long passages. The model is suitable for users who can run llama.cpp or similar GGUF‑compatible inference engines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ2_XXS1.3 GB 3.0 GB
Fits Get file →
IQ2_XS1.4 GB 3.2 GB
Fits Get file →
IQ2_S1.5 GB 3.2 GB
Fits Get file →
Q2_K_S1.5 GB 3.3 GB
Fits Get file →
IQ2_M1.6 GB 3.3 GB
Fits Get file →
Q2_K_M1.6 GB 3.3 GB
Fits Get file →
IQ3_XXS1.8 GB 3.5 GB
Fits Get file →
IQ3_XS1.8 GB 3.5 GB
Fits Get file →
IQ3_M2.0 GB 3.7 GB
Fits Get file →
Q3_K_S2.0 GB 3.7 GB
Fits Get file →
Q3_K_M2.1 GB 3.8 GB
Fits Get file →
IQ4_XS2.3 GB 4.0 GB
Fits Get file →
IQ4_NL2.3 GB 4.0 GB
Fits Get file →
Q4_K_S2.4 GB 4.1 GB
Fits Get file →
Q4_02.5 GB 4.2 GB
Fits Get file →
Q4_12.5 GB 4.3 GB
Fits Get file →
Q4_K_M2.6 GB 4.3 GB
Fits Get file →
Q5_02.9 GB 4.6 GB
Fits Get file →
Q5_K_M3.0 GB 4.7 GB
Fits Get file →
Q5_13.1 GB 4.9 GB
Fits Get file →
Q6_K_M3.4 GB 5.1 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →
F165.9 GB 7.6 GB
Tight Get file →
BF168.1 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use the Q4_K_M quant (file size 2.57 GB, memory 4.3 GB at 8k context). If 12 GB VRAM is available, Q5_K_M (2.99 GB, 4.7 GB) offers higher precision. For 16 GB VRAM, the full‑precision F16 (5.93 GB, 7.6 GB) provides the best accuracy.

What GPU do you need for Fathom-Search-4B?

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 IQ4_NL (2.3 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.9 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (8.1 GB file, about 9.8 GB in use).

Which Fathom-Search-4B quant should you choose?

Q4_K_M is the usual starting point for Fathom-Search-4B: it balances file size and quality well. Here it is a 2.6 GB file.

The Q8_0 file is 4.3 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 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

Architectureqwen3
Parameters4B
Layers36
Trained context40,960 tokens
KV cache (fp16)144 KB per token

Source

Quantized byMungert
FamilyQwen
Base modelQwen/Qwen3-4B
Licensemit
Downloads (HF)2,688
Last updated2025-10-23

Frequently asked questions about Fathom-Search-4B

How much VRAM does Fathom-Search-4B need?

About 4.3 GB at Q4_K_M with an 8K context window. That is the 2.6 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 Fathom-Search-4B on an 8 GB GPU?

Yes, with F16: the 5.9 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 Fathom-Search-4B GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XXS is 1.3 GB, IQ2_XS is 1.4 GB, IQ2_S is 1.5 GB, Q2_K_S is 1.5 GB, IQ2_M is 1.6 GB and 19 more.

What context length does Fathom-Search-4B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Fathom-Search-4B GGUF?

The files are on Hugging Face in the Mungert/Fathom-Search-4B-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 Fathom-Search-4B use?

Hugging Face lists the license as mit. 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 Fathom-Search-4B on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 4.3 GB of VRAM at 8k context, which fits within an 8 GB GPU.

Does the model support vision inputs?

No, Fathom-Search-4B does not have vision capabilities.

What license does the model use?

The model is released under the MIT license.

Other GGUFs of Qwen3-4B

Similar models

Browse all →

More from Mungert

All by Mungert →

More Qwen models

All Qwen →

Other small models

All small models →