NE

nesso 0.4B Q6 K

NessoGGUF by harrier77Updated 2026-03-13
Download on Hugging Face
Parameters561M
Context4K
Layers32
Architecturellama
Smallest quant0.6 GB
Quick answer

nesso 0.4B Q6 K needs about 1.4 GB of memory at Q6_K (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU.

nesso 0.4B Q6 K is a 561M-parameter Nesso model in GGUF format, quantized by harrier77. Its trained context length is 4K tokens. The repository has 1 quant file, from 0.6 GB (Q6_K) to 0.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K0.6 GB 1.3 GB
Fits Get file →

What GPU do you need for nesso 0.4B Q6 K?

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 Q6_K (0.6 GB file, about 1.4 GB in use).

Which nesso 0.4B Q6 K quant should you choose?

Q6_K (0.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters561M
Layers32
Trained context4,096 tokens
KV cache (fp16)40 KB per token

Source

Quantized byharrier77
FamilyNesso
Licenseapache-2.0
Downloads (HF)20
Last updated2026-03-13

Frequently asked questions about nesso 0.4B Q6 K

How much VRAM does nesso 0.4B Q6 K need?

About 1.4 GB at Q6_K with an 8K context window. That is the 0.6 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 nesso 0.4B Q6 K on an 8 GB GPU?

Yes, with Q6_K: the 0.6 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of nesso 0.4B Q6 K GGUF?

It depends on the quant: Q6_K is 0.6 GB.

What context length does nesso 0.4B Q6 K support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.3 GB at 8K and 0.2 GB at 4K.

Where can I download nesso 0.4B Q6 K GGUF?

The files are on Hugging Face in the harrier77/nesso-0.4B-Q6_K.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 nesso 0.4B Q6 K 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 harrier77

All by harrier77 →

More Nesso models

All Nesso →

Other tiny models

All tiny models →