EA

Eagle 3b Preview

EagleGGUF by legokimUpdated 2024-12-01
Download on Hugging Face
Parameters3.1B
Context16K
Layers16
Architecturellama
Smallest quant2.2 GB
Quick answer

Eagle 3b Preview needs about 4.1 GB of memory at Q5_K_M (a 2.2 GB file) with an 8K context window, so it fits on a 6 GB GPU.

Eagle 3b Preview is a 3.1B-parameter Eagle model in GGUF format, quantized by legokim. Its trained context length is 16K tokens. The repository has 1 quant file, from 2.2 GB (Q5_K_M) to 2.2 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M2.2 GB 4.1 GB
Fits Get file →

What GPU do you need for Eagle 3b Preview?

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 (2.2 GB file, about 4.1 GB in use).

Which Eagle 3b Preview quant should you choose?

Q5_K_M (2.2 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

Architecturellama
Parameters3.1B
Layers16
Trained context16,384 tokens
KV cache (fp16)160 KB per token

Source

Quantized bylegokim
FamilyEagle
Downloads (HF)6
Last updated2024-12-01

Frequently asked questions about Eagle 3b Preview

How much VRAM does Eagle 3b Preview need?

About 4.1 GB at Q5_K_M with an 8K context window. That is the 2.2 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 Eagle 3b Preview on an 8 GB GPU?

Yes, with Q5_K_M: the 2.2 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Eagle 3b Preview GGUF?

It depends on the quant: Q5_K_M is 2.2 GB.

What context length does Eagle 3b Preview support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.3 GB at 8K and 2.7 GB at 16K.

Where can I download Eagle 3b Preview GGUF?

The files are on Hugging Face in the legokim/eagle-3b-preview-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.

Other GGUFs of eagle-3b-preview

Similar models

Browse all →

More Eagle models

All Eagle →

Other tiny models

All tiny models →