# S5-nano

> S5-nano is a 4B-parameter model from Maritaca AI. It has two modes:

- **Organisation:** maritaca-ai
- **Category:** Vision-Language Models, Reasoning Models
- **Parameters:** 4.7B
- **Context length:** 262,144 tokens
- **Licence:** Apache 2.0 (Commercial use OK)
- **Released:** 2026-11-02
- **Hugging Face:** 2.3K downloads (30 days), 83 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 3 |
| Q3_K_M | 3.73 |
| Q4_K_M | 4.26 |
| Q5_K_M | 4.74 |
| Q6_K | 5.25 |
| Q8_0 | 6.34 |
| F16 | 10.61 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [LM Studio](https://lmstudio.ai)
- [SGLang](https://selfhost.directory/project/sglang)
- [Transformers](https://github.com/huggingface/transformers)
- [vLLM](https://selfhost.directory/project/vllm)
- [Jan](https://jan.ai) (community)
- [KoboldCpp](https://selfhost.directory/project/koboldcpp) (community)
- [LocalAI](https://selfhost.directory/project/localai) (community)
- [Ollama](https://selfhost.directory/project/ollama) (community)

## About

S5-nano is a 4B-parameter model from Maritaca AI. It has two modes:

• Think: reasons before answering (the default mode).
• Instruct: answers directly, without a reasoning step.

The context window supports up to 262,144 tokens, and the weights include an MTP (multi-token prediction) layer for speculative decoding.

FP8 is recommended for GPUs with native FP8 support (Ada, Hopper, and Blackwell). The GGUF repository provides BF16, Q8_0, and Q4_K_M variants.

Explore the results in Observatório Maritaca

Results for the original S5-nano checkpoint, evaluated in BF16 on text tasks.

Each primary metric is weighted equally.

## Alternatives

- [Qwen/Qwen3.5-4B](https://selfhost.directory/models/qwen/qwen3.5-4b) (4.7B, Apache 2.0, ≈4.26 GB at Q4): Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
- [Qwen/Qwen3-VL-4B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-4b-instruct) (4.4B, Apache 2.0, ≈4.26 GB at Q4): Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
- [Qwen/Qwen3.5-4B-Base](https://selfhost.directory/models/qwen/qwen3.5-4b-base) (4.7B, Apache 2.0, ≈4.26 GB at Q4): Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.
- [tencent/WeVisOne-VL-4B](https://selfhost.directory/models/tencent/wevisone-vl-4b) (4.8B, Apache 2.0, ≈4.49 GB at Q4): WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception…
- [h2oai/h2o-lightning-4b](https://selfhost.directory/models/h2oai/h2o-lightning-4b) (4.5B, Apache 2.0, ≈4.19 GB at Q4): H2O-Lightning-4B is a 4B-parameter decision model from H2O.ai, built on Qwen/Qwen3.5-4B. It answers typed decision questions about a record (a document, a ticket, a policy, a conversation) and about images that come with the record (photos, screenshots, scanned documents, charts).
- [google/medgemma-1.5-4b-it](https://selfhost.directory/models/google/medgemma-1.5-4b-it) (4.3B, health-ai-developer-foundations, ≈4.11 GB at Q4): * License: The use of MedGemma is governed by the Health AI Developer Foundations terms of use. MedGemma has not been evaluated or optimized for multi-turn applications.

More: https://selfhost.directory/models/maritaca-ai/s5-nano/alternatives

## Runs well on

- [GeForce RTX 4060](https://selfhost.directory/models/maritaca-ai/s5-nano/on/rtx-4060): Q8_0, est. 30 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/maritaca-ai/s5-nano/on/apple-m4-16gb): F16, est. 7.1 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/maritaca-ai/s5-nano/on/rx-6700-xt): F16, est. 23 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/maritaca-ai/s5-nano/on/rtx-3060): F16, est. 21 tok/s
- [Arc B580](https://selfhost.directory/models/maritaca-ai/s5-nano/on/arc-b580): F16, est. 27 tok/s
- [Tesla T4](https://selfhost.directory/models/maritaca-ai/s5-nano/on/tesla-t4): F16, est. 19 tok/s

## Similar size

- [Qwen/Qwen3.5-4B](https://selfhost.directory/models/qwen/qwen3.5-4b) (4.7B)
- [google/gemma-3-4b-it](https://selfhost.directory/models/google/gemma-3-4b-it) (4.3B)
- [Qwen/Qwen3-VL-4B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-4b-instruct) (4.4B)
- [Qwen/Qwen2.5-VL-3B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-vl-3b-instruct) (3.8B)
- [google/translategemma-4b-it](https://selfhost.directory/models/google/translategemma-4b-it) (5B)
- [google/medgemma-1.5-4b-it](https://selfhost.directory/models/google/medgemma-1.5-4b-it) (4.3B)

## FAQ

**How much VRAM does S5-nano need?**
About 4.3 GB at Q4_K_M with an 8K context. Q8_0 needs about 6.3 GB and full precision about 11 GB. Longer contexts need more memory for the KV cache.

**Can S5-nano run on the RTX 4060?**
Yes. It fits at Q8_0 (about 6.0 GB), at an estimated 30 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.

**Can I use S5-nano commercially?**
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.

**What is the context length of S5-nano?**
262,144 tokens (256K). The full window needs far more memory than an 8K context.

**How do I run S5-nano with Ollama or llama.cpp?**
With Ollama: ollama run hf.co/maritaca-ai/S5-nano-GGUF:Q4_K_M. With llama.cpp: llama-server -hf maritaca-ai/S5-nano-GGUF:Q4_K_M, which starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/maritaca-ai/S5-nano
- homepage: https://maritaca-ai.github.io/observatorio-maritaca/

---
Source: https://selfhost.directory/models/maritaca-ai/s5-nano