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 Arete-27B

120 open-weight models that do the same job as Arete-27B (27.4B 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
NousResearch logo

Arete-27B

NousResearch·Chat

≈19 GB

We post-trained over Alibaba's Qwen3.8-27B to reinforce western values on a Chinese-trained model. We call this new model Arete-27B.

27.4B256K ctx Apache 2.0
6.2KNov 2026gguf
--vram
any
--gpus
--quant
  1. chromadb logo

    context-1

    chromadb·Chat

    ≈13 GB

    Context-1 is a 20B parameter agentic search model trained to retrieve supporting documents for complex, multi-hop queries.

    20.9BA4.2B128K ctx Apache 2.0
    633Mar 2026gguf
    • Same category
    • Similar size (20.9B vs 27.4B)
    • Commercial use OK
    vs
  2. inclusionAI logo

    LLaDA2.0-mini

    inclusionAI·Chat

    ≈10 GB

    LLaDA2.0-mini is a diffusion language model featuring a 16BA1B Mixture-of-Experts (MoE) architecture. As an enhanced, instruction-tuned iteration of the LLaDA series, it is optimized for practical applications.

    16.3BA1.4B32K ctx Apache 2.0
    14.3KNov 2025
    • Same category
    • Similar size (16.3B vs 27.4B)
    • Commercial use OK
    vs
  3. tiiuae logo≈22 GB

    For more details about the training protocol of this model, please refer to the Falcon-H1 technical blogpost and Technical Report.

    33.6B256K ctx Falcon LLM License
    3.8KMay 2025gguf
    • Same category
    • Similar size (33.6B vs 27.4B)
    vs
  4. CohereLabs logo

    c4ai-command-r-v01

    CohereLabs·Chat

    ≈23 GB

    Cohere Labs Command-R is a research release of a 35 billion parameter highly performant generative model. Command-R is a large language model with open weights optimized for a variety of use cases including reasoning, summarization, and question answering.

    35B128K ctx CC BY-NC 4.0
    118.1KMar 2024gguf
    • Same category
    • Similar size (35B vs 27.4B)
    vs
  5. mindlab-research logo

    Macaron-V1-Tall

    mindlab-research·Chat

    ≈22 GB

    Macaron-V1-Tall is a Mixture of LoRA (MoL) model in the Macaron-V1 family, built on Qwen3.6-35B-A3B for personal intelligence, tool use, coding workflows, and code-native Generative UI.

    36BA4.7B256K ctx MIT
    183Jul 2026gguf
    • Same category
    • Similar size (36B vs 27.4B)
    • Commercial use OK
    vs
  6. perplexity-ai logo

    browsesafe

    perplexity-ai·Chat

    ≈19 GB

    BrowseSafe is a multi-layered defense strategy comprising both architectural and model-based defenses to protect against evolving prompt injection attacks. It is a specialized security model designed to protect AI browser agents from prompt injection attacks embedded in real-world web content.

    30.5BA3.4B256K ctx MIT
    281Nov 2025gguf
    • Same category
    • Similar size (30.5B vs 27.4B)
    • Commercial use OK
    vs
  7. Qwen logo

    Qwen2.5-32B

    Qwen·Chat

    ≈22 GB

    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:

    32.8B128K ctx Apache 2.0
    13.9KSept 2024gguf
    • Same category
    • Similar size (32.8B vs 27.4B)
    • Commercial use OK
    vs
  8. ByteDance-Seed logo

    Seed-OSS-36B-Base

    ByteDance-Seed·Chat

    ≈24 GB

    Seed-OSS is a series of open-source large language models developed by ByteDance's Seed Team, designed for powerful long-context, reasoning, agent and general capabilities, and versatile developer-friendly features.

    36.2B512K ctx Apache 2.0
    2.3KAug 2025gguf
    • Same category
    • Similar size (36.2B vs 27.4B)
    • Commercial use OK
    vs
  9. Vikhrmodels logo

    Vistral-24B-Instruct

    Vikhrmodels·Chat

    ≈16 GB

    Vistral-24B-Instruct is an open-weight chat model with 23.6B parameters from Vikhrmodels, published on Hugging Face.

    23.6B128K ctx Apache 2.0
    546Sept 2025gguf
    • Same category
    • Similar size (23.6B vs 27.4B)
    • Commercial use OK
    vs
  10. Qwen logo≈11 GB

    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:

    14.8B32K ctx Apache 2.0
    619.6KSept 2024ollama
    • Same category
    • Similar size (14.8B vs 27.4B)
    • Commercial use OK
    vs
  11. zai-org logo≈22 GB

    The GLM family welcomes a new generation of open-source models, the GLM-4-32B-0414 series, featuring 32 billion parameters. Its performance is comparable to OpenAI's GPT series and DeepSeek's V3/R1 series, and it supports very user-friendly local deployment features.

    33.1B128K ctx MIT
    2.4KApr 2025gguf
    • Same category
    • Similar size (33.1B vs 27.4B)
    • Commercial use OK
    vs
  12. NousResearch logo≈16 GB

    DeepHermes 3 Preview is the latest version of our flagship Hermes series of LLMs by Nous Research, and one of the first models in the world to unify Reasoning (long chains of thought that improve answer accuracy) and normal LLM response modes into one model.

    23.6B32K ctx Apache 2.0
    2KMar 2025gguf
    • Same category
    • Similar size (23.6B vs 27.4B)
    • Commercial use OK
    vs
  13. tencent logo

    ContextPilot-14B

    tencent·Chat

    ≈11 GB

    ContextPilot-14B is the Qwen3-14B checkpoint of ContextPilot, a proactive context-management framework for long-horizon language-model agents. It teaches agents to plan, maintain long-term memory, and offload less useful context while they continue reasoning and using tools.

    14.8B40K ctx Custom licence
    2.3KAug 2026gguf
    • Same category
    • Similar size (14.8B vs 27.4B)
    vs
  14. google logo

    gemma-2-27b

    google·Chat

    ≈20 GB

    Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

    27.2B8K ctx Gemma Terms of Use
    3.5KJun 2024gguf
    • Same category
    • Similar size (27.2B vs 27.4B)
    vs
  15. microsoft logo

    OptiMind-SFT

    microsoft·Chat

    ≈13 GB

    OptiMind-SFT is a specialized 20B parameter model designed to bridge the gap between natural language and executable optimization solvers.

    20.9BA4.2B128K ctx MIT
    639Dec 2025gguf
    • Same category
    • Similar size (20.9B vs 27.4B)
    • Commercial use OK
    vs
  16. t-tech logo

    T-pro-it-2.0

    t-tech·Chat

    ≈22 GB

    T-pro-it-2.0 is a model built upon the Qwen 3 model family and incorporates both continual pre-training and alignment techniques.

    32.8B40K ctx Apache 2.0
    847Jul 2025gguf
    • Same category
    • Similar size (32.8B vs 27.4B)
    • Commercial use OK
    vs
  17. microsoft logo

    phi-4

    microsoft·Chat

    ≈11 GB

    Our training data is an extension of the data used for Phi-3 and includes a wide variety of sources from:

    14.7B16K ctx MIT
    228.8KDec 2024ollama
    • Same category
    • Similar size (14.7B vs 27.4B)
    • Commercial use OK
    vs
  18. Qwen logo≈11 GB

    Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens. Compared to the Qwen2.5 128K version, Qwen2.5-1M demonstrates significantly improved performance in handling long-context tasks while maintaining its capability in short tasks.

    14.8B1M ctx Apache 2.0
    153.5KJan 2025gguf
    • Same category
    • Similar size (14.8B vs 27.4B)
    • Commercial use OK
    vs
  19. arcee-ai logo

    Arcee-Blitz

    arcee-ai·Chat

    ≈16 GB

    Arcee-Blitz (24B) is a new Mistral-based 24B model distilled from DeepSeek, designed to be both fast and efficient. We view it as a practical “workhorse” model that can tackle a range of tasks without the overhead of larger architectures.

    23.6B32K ctx Apache 2.0
    1.7KFeb 2025gguf
    • Same category
    • Similar size (23.6B vs 27.4B)
    • Commercial use OK
    vs
  20. Alibaba-NLP logo

    WebDancer-32B

    Alibaba-NLP·Chat

    ≈22 GB

    This model was presented in the paper WebDancer: Towards Autonomous Information Seeking Agency.

    32.8B40K ctx MIT
    703Jun 2025gguf
    • Same category
    • Similar size (32.8B vs 27.4B)
    • Commercial use OK
    vs
  21. CohereLabs logo

    aya-expanse-32b

    CohereLabs·Chat

    ≈22 GB

    Aya Expanse 32B is an open-weight research release of a model with highly advanced multilingual capabilities. It focuses on pairing a highly performant pre-trained Command family of models with the result of a year’s dedicated research from Cohere Labs, including data arbitrage, multilingual…

    32.3BCC BY-NC 4.0
    3.6KOct 2024ollama
    • Same category
    • Similar size (32.3B vs 27.4B)
    vs
  22. zai-org logo

    GLM-4-32B-Base-0414

    zai-org·Chat

    ≈20 GB

    The GLM family welcomes new members, the GLM-4-32B-0414 series models, featuring 32 billion parameters. Its performance is comparable to OpenAI’s GPT series and DeepSeek’s V3/R1 series. It also supports very user-friendly local deployment features.

    32.6B32K ctx MIT
    1.1KApr 2025gguf
    • Same category
    • Similar size (32.6B vs 27.4B)
    • Commercial use OK
    vs
  23. nvidia logo≈9.8 GB

    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.

    13.5B256K ctx nvidia-nemotron-open-model-license
    6.9KApr 2026gguf
    • Same category
    • Smaller (13.5B vs 27.4B)
    • Commercial use OK
    vs
  24. baidu logo≈14 GB

    The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

    21.8BA3B128K ctx Apache 2.0
    755Jun 2025gguf
    • Same category
    • Similar size (21.8B vs 27.4B)
    • Commercial use OK
    vs