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.
Jan-Nano-128k represents a significant advancement in compact language models for research applications. Building upon the success of Jan-Nano, this enhanced version features a native 128k context window that enables deeper, more comprehensive research capabilities without the performance…
4B128K ctx Apache 2.01.1K 224Jun 2025- Same category
- Similar size (4B vs 3.5B)
- Commercial use OK
Granite is a family of open-source large language models developed by IBM, designed for enterprise and research use. Granite models are built to be versatile, safe, and efficient — covering a range of sizes and capabilities from compact edge-deployable models to large-scale reasoning systems.
8.8B128K ctx Apache 2.059.9K 125Aug 2026- Same category
- Larger (8.8B vs 3.5B)
- Commercial use OK
MiniCPM3-4B is the 3rd generation of MiniCPM series. The overall performance of MiniCPM3-4B surpasses Phi-3.5-mini-Instruct and GPT-3.5-Turbo-0125, being comparable with many recent 7B~9B models.
4B32K ctx Apache 2.010.1K 422Sept 2024- Same category
- Similar size (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:
1.5B32K ctx Apache 2.05.1M 945Sept 2024- Same category
- Smaller (1.5B vs 3.5B)
- Commercial use OK
- Widely used
Large Action Models (LAMs) are advanced language models designed to enhance decision-making by translating user intentions into executable actions.
3.1B32K ctx CC BY-NC 4.02.3K 18Mar 2025- Same category
- Similar size (3.1B vs 3.5B)
Jan-v1 is the first release in the Jan Family, designed for agentic reasoning and problem-solving within the Jan App. Based on our Lucy model, Jan-v1 achieves improved performance through model scaling.
4B256K ctx Apache 2.0738 353Aug 2025- Same category
- Similar size (4B vs 3.5B)
- Commercial use OK
We introduce Spark-X2.6-1.7B, the second model in the Spark-X2.6 series, following the release of Spark-X2.6-4B. Building on Spark-X2.5-1.7B, this release further advances our compact, general-purpose language models for on-device deployment.
1.7B1M ctx Apache 2.05.6K 85Oct 2026- Same category
- Smaller (1.7B vs 3.5B)
- Commercial use OK
Jan-Nano is a compact 4-billion parameter language model specifically designed and trained for deep research tasks. This model has been optimized to work seamlessly with Model Context Protocol (MCP) servers, enabling efficient integration with various research tools and data sources.
4B40K ctx Apache 2.01K 510Jun 2025- Same category
- Similar size (4B vs 3.5B)
- Commercial use OK
Phi-2 is a Transformer with 2.7 billion parameters. It was trained using the same data sources as Phi-1.5, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value).
2.8B2K ctx MIT180.7K 3.5KDec 2023- Same category
- Similar size (2.8B vs 3.5B)
- Commercial use OK
We introduce Olmo 3, a new family of 7B and 32B models. This suite includes Base, Instruct, and Think variants. The Base models were trained using a staged training approach.
7.3B64K ctx Apache 2.0106.3K 93Sept 2025- Same category
- Larger (7.3B vs 3.5B)
- Commercial use OK
Hunyuan is Tencent's open-source efficient large language model series, designed for versatile deployment across diverse computational environments.
4.2B256K ctx Unknown licence987 30Jul 2025- Same category
- Similar size (4.2B vs 3.5B)
Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters.
3.2B32K ctx Falcon LLM License2.6K 17Dec 2024- Same category
- Similar size (3.2B vs 3.5B)
Model Summary: Granite-3.1-2B-Instruct is a 2B parameter long-context instruct model finetuned from Granite-3.1-2B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets tailored for solving long context problems.
2.5B128K ctx Apache 2.021.5K 57Dec 2024- Same category
- Similar size (2.5B vs 3.5B)
- Commercial use OK
We are introducing Ling-3.0-tiny, a lightweight hybrid reasoning MoE model with 7.9B total parameters and only 1.3B activated parameters per token.
7.9BA1.4B128K ctx MIT13.6K 586Aug 2026- Same category
- Larger (7.9B vs 3.5B)
- Commercial use OK
AFM-4.5B-Base is a 4.5 billion parameter instruction-tuned model developed by Arcee.ai, designed for enterprise-grade performance across diverse deployment environments from cloud to edge.
4.6B64K ctx Apache 2.01.6K 36Jul 2025- Same category
- Similar size (4.6B vs 3.5B)
- Commercial use OK
Model Summary: Granite-4.1-8B is a 8B parameter long-context instruct model finetuned from Granite-4.1-8B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.
8.8B128K ctx Apache 2.082.2K 258Apr 2026- Same category
- Larger (8.8B vs 3.5B)
- Commercial use OK
The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out).
8B128K ctx Llama 3.1 Community License4.2M 8.9KJul 2024- Same category
- Larger (8B vs 3.5B)
- Widely used
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
8.2B32K ctx Apache 2.0597.9K 152Apr 2025- Same category
- Larger (8.2B vs 3.5B)
- Commercial use OK
Based on LFM2-2.6B, LFM2-2.6B-Transcript is designed for private, on-device meeting summarization. We partnered with AMD to deliver cloud-level summary quality while running entirely locally, ensuring that your meeting data never leaves your device.
2.6B125K ctx lfm1.0714 176Jan 2026- Same category
- Similar size (2.6B vs 3.5B)
Apertus is a 70B and 8B parameter language model designed to push the boundaries of fully-open multilingual and transparent models.
8.1B64K ctx Apache 2.0204.9K 505Aug 2025- Same category
- Larger (8.1B vs 3.5B)
- Commercial use OK
Sentiment-Analysis-7B is a 7B-parameter autoregressive language model fine-tuned for sentiment classification of user messages directed at a service, product, or agent (the "Target").
7.2B32K ctx MIT3K 33Oct 2026- Same category
- Larger (7.2B vs 3.5B)
- Commercial use OK
K2-Horizon-7B is the medium dense member of the K2-Horizon family: a 7B-core decoder-only model with a 512K context window.
9B512K ctx Apache 2.028.7K 289Sept 2026- Same category
- Larger (9B vs 3.5B)
- Commercial use OK
Nemotron-Labs-Diffusion is a tri-mode language model that supports both AR decoding and diffusion-based parallel decoding by simply switching the attention pattern of the same model during inference.
8.5B256K ctx nvidia-nemotron-open-model-license60.5K 59Mar 2026- Same category
- Larger (8.5B vs 3.5B)
- Commercial use OK
A compact 9B reasoning model distilled from DeepSeek-V4-Pro in Max Effect mode
9.4B256K ctx Apache 2.027K 7.5KOct 2026- Same category
- Larger (9.4B vs 3.5B)
- Commercial use OK
- Newer release