Raon-1 nano is a dense language model with 1.5B effective parameters (3.1B total, including a 1.5B per-layer embedding table), developed by KRAFTON AI. It is designed to follow instructions, maintain conversational context, and call the right tools in both Korean and English.
Alternatives to Raon-1-nano
120 open-weight models that do the same job as Raon-1-nano (3.5B chat), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports 6 languages, advanced reasoning and long context. SmolLM3 is a fully open model that offers strong performance at the 3B–4B scale.
3.1B64K ctx Apache 2.088.2K 180Jun 2025- Same category
- Similar size (3.1B vs 3.5B)
- Commercial use OK
A little over a month has passed since Spark-X2.5. In the rapidly evolving world of AI agents, that is enough time to rethink, refine, and move the frontier forward.
4.1B1M ctx Apache 2.02.5K 48Oct 2026- Same category
- Similar size (4.1B vs 3.5B)
- Commercial use OK
Cohere Labs Tiny Aya is an open weights research release of a pretrained 3.35 billion parameter model optimized for efficient, strong, and balanced multilingual representation across 70+ languages, including many lower-resourced ones.
3.3BCC BY-NC 4.06K 33Feb 2026- Same category
- Similar size (3.3B vs 3.5B)
Nanbeige4.1-3B is built upon Nanbeige4-3B-Base and represents an enhanced iteration of our previous reasoning model, Nanbeige4-3B-Thinking-2511, achieved through further post-training optimization with supervised fine-tuning (SFT) and reinforcement learning (RL).
3.9B256K ctx Apache 2.010.3K 1.2KFeb 2026- Same category
- Similar size (3.9B vs 3.5B)
- Commercial use OK
Phi-tiny-MoE is a lightweight Mixture of Experts (MoE) model with 3.8B total parameters and 1.1B activated parameters. It is compressed and distilled from the base model shared by Phi-3.5-MoE and GRIN-MoE using the SlimMoE approach, then post-trained via supervised fine-tuning and direct preference…
3.8BA1.3B4K ctx MIT30.3K 52Jun 2025- Same category
- Similar size (3.8B vs 3.5B)
- Commercial use OK
K2-Horizon-3.7B is the small dense member of the K2-Horizon family: a 3.7B-core decoder-only model with a 512K context window.
5.1B512K ctx Apache 2.015.2K 116Sept 2026- Same category
- Similar size (5.1B vs 3.5B)
- Commercial use OK
The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out).
3.2B128K ctx Llama 3.2 Community License313.5K 1.1KSept 2024- Same category
- Similar size (3.2B vs 3.5B)
Phi-3.5-mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length.
3.8B128K ctx MIT340.3K 1.3KAug 2024- Same category
- Similar size (3.8B vs 3.5B)
- Commercial use OK
We are releasing MiniCPM5-2B, the second model in the MiniCPM5 series, following MiniCPM5-1B. It is a dense 2B Transformer that scales up the same training recipe, built for on-device, local deployment, and resource-constrained scenarios, reaching 2B-class open-source SOTA.
2.5B512K ctx Apache 2.012.8K 34Aug 2026- Same category
- Similar size (2.5B vs 3.5B)
- Commercial use OK
NeoHorse-1-4B is a 4B causal language model and an initial prototype on the path toward recursive self-improvement (RSI). It is post-trained from Qwen3.5-4B for text-based agent harnesses, tool use, coding, and instruction following.
4.2B256K ctx Apache 2.02.8K 2.6KSept 2026- Same category
- Similar size (4.2B vs 3.5B)
- Commercial use OK
LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.
2.7B125K ctx lfm1.07.4K 53Aug 2026- Same category
- Similar size (2.7B vs 3.5B)
Model Summary: Granite-3.1-3B-A800M-Instruct is a 3B parameter long-context instruct model finetuned from Granite-3.1-3B-A800M-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets tailored for solving long context problems.
3.3BA800M128K ctx Apache 2.0114.9K 33Dec 2024- Same category
- Similar size (3.3B vs 3.5B)
- Commercial use OK
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
2B40K ctx Apache 2.03M 622Apr 2025- Same category
- Similar size (2B vs 3.5B)
- Commercial use OK
- Widely used
Model Summary Granite-SWASH-3B-a600M is a 3B parameter decoder-only sparse language model with per-layer Sliding Window Attention (SWA) and learnable attention sinks (LSE-based).
3BA600M8K ctx Apache 2.03K 15Jul 2026- Same category
- Similar size (3B vs 3.5B)
- Commercial use OK
2.For harder math reasoning, try AMOBench , a problem set harder than the International Mathematical Olympiad (IMO), with included standard answers. Use it to evaluate VibeThinker against other SOTA models. Note: due to extreme difficulty, set max tokens to 60K–100K.
3.1B128K ctx MIT2.6K 865Jun 2026- Same category
- Similar size (3.1B vs 3.5B)
- Commercial use OK
Cohere Labs Tiny Aya is an open weights research release of a pretrained 3.35 billion parameter model optimized for efficient, strong, and balanced multilingual representation across 70+ languages, including many lower-resourced ones.
3.3BCC BY-NC 4.02.9K 72Feb 2026- Same category
- Similar size (3.3B vs 3.5B)
UserRepGen-4B is a fine-tuned Qwen3.5-4B language model that generates a structured, natural-language user representation from a multi-turn user-assistant conversation.
4.5B256K ctx MIT2.5K 28Oct 2026- Same category
- Similar size (4.5B vs 3.5B)
- Commercial use OK
This is the RL initialization checkpoint used in the blog JustRL II: Scaling Small LLMs to 128K Reasoning with a Critic (中文版).
2.8B64K ctx Unknown licence2.2K 8Sept 2026- Same category
- Similar size (2.8B vs 3.5B)
BitCPM-CANN is the first end-to-end 1.58-bit (ternary) large language model training system natively built on Huawei Ascend NPU.
3B32K ctx Apache 2.03K 10May 2026- Same category
- Similar size (3B vs 3.5B)
- Commercial use OK
We are releasing MiniCPM5-2B, the second model in the MiniCPM5 series, following MiniCPM5-1B. It is a dense 2B Transformer that scales up the same training recipe, built for on-device, local deployment, and resource-constrained scenarios, reaching 2B-class open-source SOTA.
2.5B128K ctx Apache 2.06.6K 31Aug 2026- Same category
- Similar size (2.5B vs 3.5B)
- Commercial use OK
Jamba2 3B is an ultra-compact open source model designed to bring enterprise-grade reliability to on-device deployments. At just 3B parameters, it runs efficiently on consumer devices—iPhones, Androids, Macs, and PCs—while maintaining the grounding and instruction-following capabilities required…
3B256K ctx Apache 2.06.6K 53Jan 2026- Same category
- Similar size (3B vs 3.5B)
- Commercial use OK
Jan-Code-4B is a code-tuned model built on top of Jan-v3-4B-base-instruct. It’s designed to be a practical coding model you can run locally and iterate on quickly—useful for everyday code tasks and as a lightweight “worker” model in agentic workflows.
4.4B256K ctx Apache 2.08K 83Mar 2026- Same category
- Similar size (4.4B vs 3.5B)
- Commercial use OK
Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:
3.1B32K ctx Qwen Research License218.8K 227Sept 2024- Same category
- Similar size (3.1B vs 3.5B)
LFM3-1.7B is a text model for local agents and specialized applications, based on our new tri-hybrid architecture.
1.7B256K ctx lfm1.0103.7K 1.8KOct 2026- Same category
- Smaller (1.7B vs 3.5B)