EV

Eva 4B Q5 K M

EvaGGUF by FutureMaUpdated 2026-01-12
Download on Hugging Face
Parameters4.02B
Context256K
Layers36
Architectureqwen3
Smallest quant2.9 GB
Quick answer

Eva 4B Q5 K M needs about 4.6 GB of memory at Q5_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Eva 4B Q5 K M is a 4.02B-parameter Eva model in GGUF format, quantized by FutureMa. Its trained context length is 256K tokens. The repository has 1 quant file, from 2.9 GB (Q5_K_M) to 2.9 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M2.9 GB 4.6 GB
Fits Get file →

What GPU do you need for Eva 4B Q5 K M?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q5_K_M (2.9 GB file, about 4.6 GB in use).

Which Eva 4B Q5 K M quant should you choose?

Q5_K_M (2.9 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters4.02B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized byFutureMa
FamilyEva
Base modelFutureMa/Eva-4B
Licenseapache-2.0
Downloads (HF)36
Last updated2026-01-12

Frequently asked questions about Eva 4B Q5 K M

How much VRAM does Eva 4B Q5 K M need?

About 4.6 GB at Q5_K_M with an 8K context window. That is the 2.9 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 Eva 4B Q5 K M on an 8 GB GPU?

Yes, with Q5_K_M: the 2.9 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Eva 4B Q5 K M GGUF?

It depends on the quant: Q5_K_M is 2.9 GB.

What context length does Eva 4B Q5 K M support?

The GGUF header lists a trained context length of 262,144 tokens (256K). 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 Eva 4B Q5 K M GGUF?

The files are on Hugging Face in the FutureMa/Eva-4B-Q5_K_M-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 Eva 4B Q5 K M 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.

Other GGUFs of Eva-4B

Similar models

Browse all →

More from FutureMa

All by FutureMa →

More Eva models

All Eva →

Other small models

All small models →