NE

Nesso2 0.4B Agentic

NessoGGUF by mradermacherUpdated 2026-10-05
Download on Hugging Face
Parameters438M
Context32K
Layers32
Architecturellama
Smallest quant0.3 GB
Quick answer

Nesso2 0.4B Agentic needs about 1.2 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.3 GB (Q2_K) to 0.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.3 GB.

Nesso2 0.4B Agentic – a small Italian/English LLM for tool‑based agentic tasks

Nesso2 0.4B Agentic is a 0.4B‑parameter bilingual Italian/English model optimized for function calling and multi‑step agentic reasoning. It supports a 32k‑token context window and is designed for sovereign edge inference.

Good at

  • Tool‑based function calling
  • Structured JSON output
  • Multi‑step agentic reasoning

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • Apache‑2.0 license

Best for

  • Edge inference with tool use
  • Structured data generation
  • Italian‑centric agentic applications

Who it’s for. Developers building lightweight agents that need reliable tool use and structured output in Italian or English. Suitable for on‑device inference where memory is limited.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.3 GB 1.1 GB
Fits Get file →
Q3_K_S0.3 GB 1.1 GB
Fits Get file →
IQ4_XS0.3 GB 1.2 GB
Fits Get file →
Q3_K_M0.3 GB 1.2 GB
Fits Get file →
Q3_K_L0.3 GB 1.2 GB
Fits Get file →
Q4_K_S0.3 GB 1.2 GB
Fits Get file →
Q4_K_M0.4 GB 1.2 GB
Fits Get file →
Q5_K_S0.4 GB 1.2 GB
Fits Get file →
Q5_K_M0.4 GB 1.2 GB
Fits Get file →
Q6_K0.5 GB 1.3 GB
Fits Get file →
Q8_00.5 GB 1.3 GB
Fits Get file →
F160.9 GB 1.7 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.36 GB file, ~1.2 GB memory at 8k context). For 4 GB VRAM, Q2_K or Q3_K_S (0.31 GB file, ~1.1 GB memory) are suitable. Higher‑precision quants like F16 require more memory and are not recommended for low‑budget setups.

What GPU do you need for Nesso2 0.4B Agentic?

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 F16 (0.9 GB file, about 1.7 GB in use).

Which Nesso2 0.4B Agentic quant should you choose?

Q4_K_M is the usual starting point for Nesso2 0.4B Agentic: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.5 GB, about 1.3 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.

If memory is tight, the smallest file is Q2_K at 0.3 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
Parameters438M
Layers32
Trained context32,768 tokens
KV cache (fp16)40 KB per token

Source

Quantized bymradermacher
FamilyNesso
Licenseapache-2.0
Downloads (HF)227
Last updated2026-10-05

Frequently asked questions about Nesso2 0.4B Agentic

How much VRAM does Nesso2 0.4B Agentic need?

About 1.2 GB at Q4_K_M with an 8K context window. That is the 0.4 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 Nesso2 0.4B Agentic on an 8 GB GPU?

Yes, with F16: the 0.9 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nesso2 0.4B Agentic GGUF?

It depends on the quant: Q2_K is 0.3 GB, Q3_K_S is 0.3 GB, IQ4_XS is 0.3 GB, Q3_K_M is 0.3 GB, Q3_K_L is 0.3 GB, Q4_K_S is 0.3 GB and 6 more.

What context length does Nesso2 0.4B Agentic support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.3 GB at 32K.

Where can I download Nesso2 0.4B Agentic GGUF?

The files are on Hugging Face in the mradermacher/nesso2-0.4B-agentic-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 Nesso2 0.4B Agentic 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.

Can I run Nesso2 0.4B Agentic on 8 GB VRAM?

Yes, using Q4_K_M or Q3_K_M quants will fit within 8 GB VRAM, with memory usage around 1.2 GB at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license does it use?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nesso models

All Nesso →

Other tiny models

All tiny models →