KE

kestrel ghost 4B

KestrelGGUF by Travis-MLUpdated 2026-06-28
Download on Hugging Face
Parameters4.02B
Context256K
Layers36
Architectureqwen3
Smallest quant2.5 GB
Quick answer

kestrel ghost 4B needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.5 GB (Q4_K_M) to 4.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

kestrel ghost 4B is a 4.02B-parameter Kestrel model in GGUF format, quantized by Travis-ML. Its trained context length is 256K tokens. The repository has 2 quant files, from 2.5 GB (Q4_K_M) to 4.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.5 GB 4.2 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →

What GPU do you need for kestrel ghost 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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).

Which kestrel ghost 4B quant should you choose?

Q4_K_M is the usual starting point for kestrel ghost 4B: it balances file size and quality well. Here it is a 2.5 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.

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 byTravis-ML
FamilyKestrel
Downloads (HF)43
Last updated2026-06-28

Frequently asked questions about kestrel ghost 4B

How much VRAM does kestrel ghost 4B need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 kestrel ghost 4B on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of kestrel ghost 4B GGUF?

It depends on the quant: Q4_K_M is 2.5 GB, Q8_0 is 4.3 GB.

What context length does kestrel ghost 4B 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 kestrel ghost 4B GGUF?

The files are on Hugging Face in the Travis-ML/kestrel-ghost-4B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More Kestrel models

All Kestrel →

Other small models

All small models →