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 Hemmingway-1.5

120 open-weight models that do the same job as Hemmingway-1.5 (26.9B 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.

Compare Hemmingway-1.5 with the top 3
the original
HemmingwayAI logo

Hemmingway-1.5

HemmingwayAI·Chat

≈18 GB

The undetectable AI. Writing indistinguishable from a human's. 27B parameters, open weights, free for non-commercial use.

26.9B256K ctx CC BY-NC 4.0
3.6KOct 2026gguf
--vram
any
--gpus
--quant
  1. NVIDIA Nemotron™ is a family of open models with open weights, training data, and recipes, delivering leading efficiency and accuracy for building specialized AI agents.

    31.6BA3B256K ctx openmdw-1.1
    963.1KAug 2026gguf
    • Same category
    • Similar size (31.6B vs 26.9B)
    • Commercial use OK
    vs
  2. farbodtavakkoli logo

    OTel-2.0-LLM-31B-IT

    farbodtavakkoli·Chat

    ≈27 GB

    Versioning notice: This card describes the current OTel 2.0 OSFT checkpoint. The model weights may be updated over time. For reproducible evaluation or production deployment, pin a specific model revision, checkpoint hash, or release tag rather than relying on the floating latest version.

    31.3B256K ctx Apache 2.0
    866.9KJul 2026gguf
    • Same category
    • Similar size (31.3B vs 26.9B)
    • Commercial use OK
    vs
  3. ornith-ai logo

    Ornith-1.0-35B

    ornith-ai·Chat

    ≈22 GB

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

    35BA3.8B256K ctx MIT
    1.5MJun 2026gguf
    • Same category
    • Similar size (35B vs 26.9B)
    • Commercial use OK
    • Widely used
    vs
  4. zai-org logo

    GLM-4.7-Flash

    zai-org·Chat

    ≈26 GB

    👋 Join our Discord community. 📖 Check out the GLM-4.7 technical blog , technical report(GLM-4.5) . 📍 Use GLM-4.7-Flash API services on Z.ai API Platform. 👉 One click to GLM-4.7 .

    31.2BA4.6B198K ctx MIT
    1.1MJan 2026ollama
    • Same category
    • Similar size (31.2B vs 26.9B)
    • Commercial use OK
    vs
  5. poolside logo

    Laguna-XS-2.1

    poolside·Chat

    ≈22 GB

    Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.

    33.4BA2.2B256K ctx Custom licence
    587.1KJun 2026ollama
    • Same category
    • Similar size (33.4B vs 26.9B)
    • Commercial use OK
    vs
  6. Nemotron-3-Nano-30B-A3B-BF16 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response.

    31.6BA3B256K ctx nvidia-nemotron-open-model-license
    1.4MDec 2025gguf
    • Same category
    • Similar size (31.6B vs 26.9B)
    • Commercial use OK
    vs
  7. poolside logo

    Laguna-XS.2

    poolside·Chat

    ≈22 GB

    Laguna XS.2 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine. It uses Sliding Window Attention with per-head gating in 30 out of 40 layers for fast inference and low KV cache requirements.

    33.4BA2.2B256K ctx Apache 2.0
    731KApr 2026ollama
    • Same category
    • Similar size (33.4B vs 26.9B)
    • Commercial use OK
    vs
  8. openai logo

    gpt-oss-20b

    openai·Chat

    ≈13 GB

    Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

    20.9BA4.2B128K ctx Apache 2.0
    5.6MAug 2025ollama
    • Same category
    • Similar size (20.9B vs 26.9B)
    • Commercial use OK
    • Widely used
    vs
  9. ornith-ai logo

    Ornith-1.5-35B-A3B

    ornith-ai·Chat

    ≈22 GB

    Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.

    36BA3B256K ctx MIT
    318.5KAug 2026ollama
    • Same category
    • Similar size (36B vs 26.9B)
    • Commercial use OK
    vs
  10. ibm-granite logo

    granite-4.2-30b

    ibm-granite·Chat

    ≈20 GB

    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.

    29.3B128K ctx Apache 2.0
    37.4KAug 2026ollama
    • Same category
    • Similar size (29.3B vs 26.9B)
    • Commercial use OK
    vs
  11. LiquidAI logo

    LFM2.5-24B-A2B

    LiquidAI·Chat

    ≈15 GB

    LFM2.5-24B-A2B is a 24B-parameter reasoning model with only 2B active parameters, built for fast, private agents on-device. It is the largest and final model in the LFM2.5 family, which now spans two orders of magnitude: from LFM2.5-230M to LFM2.5-24B-A2B.

    24BA2B128K ctx lfm1.0
    31.6KOct 2026gguf
    • Same category
    • Similar size (24B vs 26.9B)
    vs
  12. gnani logo≈20 GB

    gnani-evon-v3.3 is a hybrid Mamba architecture 30B MOE A3B model trained end-to-end for best-in-class Indic capability — continued pretraining, supervised fine-tuning, and reinforcement learning — delivering deep comprehension, extractive QA, and reasoning across Hindi, Bengali, Telugu, Tamil…

    31.7BA3B128K ctx Apache 2.0
    71.9KAug 2026gguf
    • Same category
    • Similar size (31.7B vs 26.9B)
    • Commercial use OK
    vs
  13. Qwen logo

    Qwen3-32B

    Qwen·Chat

    ≈22 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.

    32.8B40K ctx Apache 2.0
    3.4MApr 2025ollama
    • Same category
    • Similar size (32.8B vs 26.9B)
    • Commercial use OK
    • Widely used
    vs
  14. Qwen logo≈19 GB

    We introduce the updated version of the Qwen3-30B-A3B non-thinking mode, named Qwen3-30B-A3B-Instruct-2507, featuring the following key enhancements:

    30.5BA3B256K ctx Apache 2.0
    802.5KJul 2025gguf
    • Same category
    • Similar size (30.5B vs 26.9B)
    • Commercial use OK
    vs
  15. 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
    7.5KNov 2026gguf
    • Same category
    • Similar size (27.4B vs 26.9B)
    • Commercial use OK
    • Newer release
    vs
  16. Qwen logo

    Qwen3-30B-A3B

    Qwen·Chat

    ≈19 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.

    30.5BA3B40K ctx Apache 2.0
    1.1MApr 2025ollama
    • Same category
    • Similar size (30.5B vs 26.9B)
    • Commercial use OK
    vs
  17. Nanbeige logo

    Nanbeige4.3-33B

    Nanbeige·Chat

    ≈22 GB

    In Nanbeige4.3, we take a foundational step toward pushing the boundaries of lightweight agents. Our strategy centers on building a high-capacity teacher agent first, which will subsequently anchor the distillation of advanced agentic capabilities into smaller models.

    33.1B512K ctx Apache 2.0
    23.1KOct 2026gguf
    • Same category
    • Similar size (33.1B vs 26.9B)
    • Commercial use OK
    vs
  18. Altworld logo

    Hemmingway-1

    Altworld·Chat

    ≈18 GB

    The AI that writes like a person. 27B parameters, open weights, free for non-commercial use.

    26.9B256K ctx CC BY-NC 4.0
    3.4KSept 2026gguf
    • Same category
    • Similar size (26.9B vs 26.9B)
    vs
  19. tencent logo

    Hy-Memory-30B-A3B

    tencent·Chat

    ≈19 GB

    Hy-Memory-30B-A3B is a compact long-term-memory writer model (~3B active parameters) developed by Tencent Hunyuan to execute the write path inside external memory frameworks.

    30.1BA3B256K ctx Apache 2.0
    7.6KOct 2026gguf
    • Same category
    • Similar size (30.1B vs 26.9B)
    • Commercial use OK
    vs
  20. HemmingwayAI logo

    Hemmingway-1

    HemmingwayAI·Chat

    ≈18 GB

    The AI that writes like a person. 27B parameters, open weights, free for non-commercial use.

    26.9B256K ctx CC BY-NC 4.0
    3.4KSept 2026gguf
    • Same category
    • Similar size (26.9B vs 26.9B)
    vs
  21. KRAFTON logo

    Raon-1-mini-preview

    KRAFTON·Chat

    ≈20 GB

    Raon-1 mini is a 30B-A4B Mixture-of-Experts (MoE) language model, designed and trained from scratch by KRAFTON AI. It demonstrates strong capabilities in Korean conversation and agentic tasks. As part of the Raon open model family, it is released under the Apache 2.0 license.

    28.8BApache 2.0
    4.9KOct 2026gguf
    • Same category
    • Similar size (28.8B vs 26.9B)
    • Commercial use OK
    vs
  22. ibm-granite logo

    granite-switch-4.1-30b

    ibm-granite·Chat

    ≈20 GB

    📝 Read the launch blog: Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint

    30B128K ctx Apache 2.0
    5KOct 2026gguf
    • Same category
    • Similar size (30B vs 26.9B)
    • Commercial use OK
    vs
  23. InternScience logo

    Sage-A1.5

    InternScience·Chat

    ≈22 GB

    Sage‑A1.5 is a 35B Mixture‑of‑Experts agentic model from Shanghai AI Laboratory, built to advance long-horizon scientific problem solving through adaptive capability composition.

    36BA4.7B256K ctx Apache 2.0
    24.7KOct 2026gguf
    • Same category
    • Similar size (36B vs 26.9B)
    • Commercial use OK
    vs
  24. RecursiveSI logo

    flint

    RecursiveSI·Chat

    ≈25 GB

    Flint is Recursive’s mixture-of-experts language model for coding agents, with 39.8 billion total parameters and approximately 2.5 billion active per token. It is designed to investigate codebases, fix bugs, implement features, and write tests.

    39.8BA1.3B256K ctx Apache 2.0
    56.1KOct 2026ollama
    • Same category
    • Similar size (39.8B vs 26.9B)
    • Commercial use OK
    vs