DA

Danube3 4b Aezakmi 2408

DanubeGGUF by adamo1139Updated 2024-08-26
Download on Hugging Face
Parameters3.96B
Context8K
Layers24
Architecturellama
Smallest quant1.4 GB
Quick answer

Danube3 4b Aezakmi 2408 needs about 3.6 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 16 quants, from 1.4 GB (IQ2_M) to 3.3 GB (Q6_K).

Danube3 4b Aezakmi 2408 is a 3.96B-parameter Danube model in GGUF format, quantized by adamo1139. Its trained context length is 8K tokens. The repository has 16 quant files, from 1.4 GB (IQ2_M) to 3.3 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M1.4 GB 2.7 GB
Fits Get file →
Q2_K_S1.4 GB 2.7 GB
Fits Get file →
IQ3_XXS1.6 GB 2.8 GB
Fits Get file →
IQ3_XS1.7 GB 2.9 GB
Fits Get file →
Q3_K_S1.8 GB 3.0 GB
Fits Get file →
IQ3_M1.8 GB 3.1 GB
Fits Get file →
Q3_K_M1.9 GB 3.2 GB
Fits Get file →
IQ4_XS2.2 GB 3.4 GB
Fits Get file →
Q4_02.3 GB 3.5 GB
Fits Get file →
Q4_02.3 GB 3.5 GB
Fits Get file →
Q4_02.3 GB 3.5 GB
Fits Get file →
IQ4_NL2.3 GB 3.5 GB
Fits Get file →
Q4_K_S2.3 GB 3.5 GB
Fits Get file →
Q4_K_M2.4 GB 3.6 GB
Fits Get file →
Q5_K_M2.8 GB 4.1 GB
Fits Get file →
Q6_K3.3 GB 4.5 GB
Fits Get file →

What GPU do you need for Danube3 4b Aezakmi 2408?

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 Q4_K_M (2.4 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.3 GB file, about 4.5 GB in use).

Which Danube3 4b Aezakmi 2408 quant should you choose?

Q4_K_M is the usual starting point for Danube3 4b Aezakmi 2408: it balances file size and quality well. Here it is a 2.4 GB file.

If memory is tight, the smallest file is IQ2_M at 1.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.96B
Layers24
Trained context8,192 tokens
KV cache (fp16)90 KB per token

Source

Quantized byadamo1139
FamilyDanube
Licenseapache-2.0
Downloads (HF)85
Last updated2024-08-26

Frequently asked questions about Danube3 4b Aezakmi 2408

How much VRAM does Danube3 4b Aezakmi 2408 need?

About 3.6 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 Danube3 4b Aezakmi 2408 on an 8 GB GPU?

Yes, with Q6_K: the 3.3 GB file needs about 4.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Danube3 4b Aezakmi 2408 GGUF?

It depends on the quant: IQ2_M is 1.4 GB, Q2_K_S is 1.4 GB, IQ3_XXS is 1.6 GB, IQ3_XS is 1.7 GB, Q3_K_S is 1.8 GB, IQ3_M is 1.8 GB and 10 more.

What context length does Danube3 4b Aezakmi 2408 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.8 GB at 8K.

Where can I download Danube3 4b Aezakmi 2408 GGUF?

The files are on Hugging Face in the adamo1139/danube3-4b-aezakmi-2408-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 Danube3 4b Aezakmi 2408 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.

Similar models

Browse all →

More from adamo1139

All by adamo1139 →

More Danube models

All Danube →

Other small models

All small models →