selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

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.

the original
KRAFTON logo

Raon-1-nano

KRAFTON·Chat

≈5.6 GB

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.

3.5B256K ctx Apache 2.0
1.3KOct 2026gguf
--vram
any
--gpus
--quant
  1. openbmb logo≈2.3 GB

    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 2.0
    4.8KSept 2026
    • Same category
    • Similar size (2.5B vs 3.5B)
    • Commercial use OK
    vs
  2. CohereLabs logo

    tiny-aya-l2-thinker

    CohereLabs·Chat

    ≈3.1 GB

    Cohere Labs Tiny Aya L2-Thinker is an open-weights research release of a 3.35 billion parameter multilingual reasoning model optimized to think in the same language as the user prompt before writing the final answer.

    3.4BCC BY-NC 4.0
    330Sept 2026
    • Same category
    • Similar size (3.4B vs 3.5B)
    vs
  3. microsoft logo

    Phi-3-mini-4k-instruct

    microsoft·Chat

    ≈4.3 GB

    The Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties.

    3.8B4K ctx MIT
    310.3KApr 2024ollama
    • Same category
    • Similar size (3.8B vs 3.5B)
    • Commercial use OK
    vs
  4. ai9stars logo

    G9v3-3B

    ai9stars·Chat

    ≈2.7 GB

    G9v3-3B is a dense 3B causal language model from the AI9Stars team, built for local deployment and resource-constrained scenarios. It targets everyday assistant use, coding, tool-use workflows, and reasoning tasks where a compact model is preferred.

    3B128K ctx Apache 2.0
    1.2KJul 2026gguf
    • Same category
    • Similar size (3B vs 3.5B)
    • Commercial use OK
    vs
  5. CohereLabs logo

    tiny-aya-fire

    CohereLabs·Chat

    ≈3.1 GB

    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 4.0
    1.4KFeb 2026gguf
    • Same category
    • Similar size (3.3B vs 3.5B)
    vs
  6. ibm-granite logo

    granite-4.0-micro-base

    ibm-granite·Chat

    ≈3.1 GB

    Model Summary: Granite-4.0-Micro-Base is a decoder-only, long-context language model designed for a wide range of text-to-text generation tasks. It also supports Fill-in-the-Middle (FIM) code completion through the use of specialized prefix and suffix tokens.

    3.4B128K ctx Apache 2.0
    3.2KSept 2025gguf
    • Same category
    • Similar size (3.4B vs 3.5B)
    • Commercial use OK
    vs
  7. ibm-granite logo≈3.6 GB

    Model Summary: Granite Switch 4.1 3B Preview is a modular LLM built on IBM Granite 4.1 3B with embedded adapters from the Granite Libraries collection.

    4.1B128K ctx Apache 2.0
    1.8KMay 2026gguf
    • Same category
    • Similar size (4.1B vs 3.5B)
    • Commercial use OK
    vs
  8. InternScience logo

    Agents-A1-4B

    InternScience·Chat

    ≈4.2 GB

    Agents‑A1 is a long-horizon agentic model from InternScience, built to scale heterogeneous agentic abilities across multiple domains including Long‑horizon Search, Engineering, Scientific Research, Instruction Following, and Tool-calling.

    4.5B256K ctx Apache 2.0
    2.3KJul 2026gguf
    • Same category
    • Similar size (4.5B vs 3.5B)
    • Commercial use OK
    vs
  9. microsoft logo≈5.8 GB

    The Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets. This dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reasoning-dense properties.

    3.8B128K ctx MIT
    240.5KApr 2024gguf
    • Same category
    • Similar size (3.8B vs 3.5B)
    • Commercial use OK
    vs
  10. BAAI logo

    AREX-Turbo

    BAAI·Chat

    ≈4.2 GB

    AREX is a family of deep research agents developed by the Beijing Academy of Artificial Intelligence (BAAI). It is designed for long-horizon tasks in which an agent must search across sources, assemble candidate answers, verify multiple constraints, and revise its research plan when the available…

    4.5B256K ctx Apache 2.0
    1.9KJul 2026gguf
    • Same category
    • Similar size (4.5B vs 3.5B)
    • Commercial use OK
    vs
  11. sbintuitions logo≈3.7 GB

    This repository provides Japanese language models trained by SB Intuitions.

    3.4B8K ctx MIT
    16KFeb 2025gguf
    • Same category
    • Similar size (3.4B vs 3.5B)
    • Commercial use OK
    vs
  12. ibm-granite logo

    granite-4.0-h-micro

    ibm-granite·Chat

    ≈3.0 GB

    📣 Update [10-07-2025]: Added a default system prompt to the chat template to guide the model towards more professional, accurate, and safe responses.

    3.2B128K ctx Apache 2.0
    5.1KSept 2025gguf
    • Same category
    • Similar size (3.2B vs 3.5B)
    • Commercial use OK
    vs
  13. Nanbeige logo

    Nanbeige4.2-3B-Base

    Nanbeige·Chat

    ≈3.7 GB

    Nanbeige4.2-3B-Base is a new base model in the Nanbeige4 series, trained from scratch with improvements to both model architecture and training data.

    4.2B128K ctx Apache 2.0
    889Jul 2026gguf
    • Same category
    • Similar size (4.2B vs 3.5B)
    • Commercial use OK
    vs
  14. ibm-research logo

    PowerMoE-3b

    ibm-research·Chat

    ≈2.8 GB

    PowerMoE-3b is an open-weight chat model with 3.4B parameters from ibm-research, published on Hugging Face.

    3.4BA958M4K ctx Apache 2.0
    55.4KAug 2024gguf
    • Same category
    • Similar size (3.4B vs 3.5B)
    • Commercial use OK
    vs
  15. nvidia logo≈3.4 GB

    Nemotron-Mini-4B-Instruct is a model for generating responses for roleplaying, retrieval augmented generation, and function calling. It is a small language model (SLM) optimized through distillation, pruning and quantization for speed and on-device deployment.

    4B4K ctx NVIDIA Open Model License
    99.7KSept 2024ollama
    • Same category
    • Similar size (4B vs 3.5B)
    • Commercial use OK
    vs
  16. openbmb logo

    AgentCPM-Explore

    openbmb·Chat

    ≈4.0 GB

    We elaborate on the entire construction pipeline of AgentCPM-Explore on GitHub.

    4B256K ctx Apache 2.0
    2.4KJan 2026gguf
    • Same category
    • Similar size (4B vs 3.5B)
    • Commercial use OK
    vs
  17. google logo≈4.6 GB

    T5Gemma is a family of lightweight yet powerful encoder-decoder research models from Google. These models are created by adapting pretrained decoder-only models into a encoder-decoder.

    5.6B8K ctx Gemma Terms of Use
    223.4KJun 2025
    • Same category
    • Similar size (5.6B vs 3.5B)
    vs
  18. ornith-ai logo

    Ornith-1.0-9B

    ornith-ai·Chat

    ≈6.8 GB

    Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.

    9B256K ctx MIT
    822.7KJun 2026gguf
    • Same category
    • Larger (9B vs 3.5B)
    • Commercial use OK
    vs
  19. tomg-group-umd logo

    huginn-0125

    tomg-group-umd·Chat

    ≈4.1 GB

    This is Huginn, version 01/25, a latent recurrent-depth model with 3.5B parameters, trained for 800B tokens on AMD MI250X machines. This is a proof-of-concept model, but surprisingly capable in reasoning and code given its training budget and size.

    3.9BApache 2.0
    20.7KJan 2025
    • Same category
    • Similar size (3.9B vs 3.5B)
    • Commercial use OK
    vs
  20. ByteDance logo

    Ouro-2.6B

    ByteDance·Chat

    ≈5.1 GB

    Ouro-2.6B is a 2.6 billion parameter Looped Language Model (LoopLM) that achieves exceptional parameter efficiency through iterative shared-weight computation.

    2.7B64K ctx Apache 2.0
    10.3KOct 2025gguf
    • Same category
    • Similar size (2.7B vs 3.5B)
    • Commercial use OK
    vs
  21. CohereLabs logo

    tiny-aya-en-thinker

    CohereLabs·Chat

    ≈3.1 GB

    Cohere Labs Tiny Aya En-Thinker is an open-weights research release of a 3.35 billion parameter multilingual reasoning model.

    3.4BCC BY-NC 4.0
    124Sept 2026
    • Same category
    • Similar size (3.4B vs 3.5B)
    vs
  22. CohereLabs logo

    tiny-aya-water

    CohereLabs·Chat

    ≈3.1 GB

    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 4.0
    527Feb 2026gguf
    • Same category
    • Similar size (3.3B vs 3.5B)
    vs
  23. Qwen logo

    Qwen3-8B

    Qwen·Chat

    ≈6.5 GB

    Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

    8.2B40K ctx Apache 2.0
    6.1MApr 2025ollama
    • Same category
    • Larger (8.2B vs 3.5B)
    • Commercial use OK
    • Widely used
    vs
  24. lightonai logo

    colgrep-agent-2B

    lightonai·Chat

    ≈2.3 GB

    ColGrep-Agent-2B is a lightweight code-localization agent designed to identify the files and line ranges relevant to a GitHub issue, bug report, feature request, or natural-language question about a repository.

    2.5B128K ctx Apache 2.0
    1.1KOct 2026gguf
    • Same category
    • Similar size (2.5B vs 3.5B)
    • Commercial use OK
    vs