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 granite-4.1-3b-llmon-preview

120 open-weight models that do the same job as granite-4.1-3b-llmon-preview (3.7B 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
ibm-granite logo≈3.3 GB

Model Summary: Granite-4.1-3B-LLMON-preview is a 3B parameter instruct model fine-tuned from Granite-4.1-3B-base to consume prompts in LLMON (LLM Object Notation) instead of a conventional chat template.

3.7B128K ctx Apache 2.0
2.2KOct 2026gguf
--vram
any
--gpus
--quant
  1. Menlo logo

    Jan-nano

    Menlo·Chat

    ≈4.0 GB

    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 2.0
    1KJun 2025gguf
    • Same category
    • Similar size (4B vs 3.7B)
    • Commercial use OK
    vs
  2. allenai logo

    Olmo-3-1025-7B

    allenai·Chat

    ≈8.8 GB

    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 2.0
    106.3KSept 2025gguf
    • Same category
    • Similar size (7.3B vs 3.7B)
    • Commercial use OK
    vs
  3. tencent logo

    Hunyuan-4B-Instruct

    tencent·Chat

    ≈4.1 GB

    Hunyuan is Tencent's open-source efficient large language model series, designed for versatile deployment across diverse computational environments.

    4.2B256K ctx Unknown licence
    987Jul 2025gguf
    • Same category
    • Similar size (4.2B vs 3.7B)
    vs
  4. LGAI-EXAONE logo

    EXAONE-3.5-2.4B-Instruct

    LGAI-EXAONE·Chat

    ≈2.5 GB

    We introduce EXAONE 3.5, a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.

    2.4B32K ctx exaone
    70.8KDec 2024ollama
    • Same category
    • Similar size (2.4B vs 3.7B)
    vs
  5. inclusionAI logo

    Ling-3.0-tiny

    inclusionAI·Chat

    ≈6.7 GB

    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 MIT
    13.6KAug 2026gguf
    • Same category
    • Larger (7.9B vs 3.7B)
    • Commercial use OK
    vs
  6. google logo

    gemma-2-2b

    google·Chat

    ≈2.9 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.

    2.6B8K ctx Gemma Terms of Use
    80.1KJul 2024gguf
    • Same category
    • Similar size (2.6B vs 3.7B)
    vs
  7. google logo

    txgemma-2b-predict

    google·Chat

    ≈2.6 GB

    TxGemma is a collection of lightweight, state-of-the-art, open language models built upon Gemma 2, fine-tuned for therapeutic development. It comes in 3 sizes, 2B, 9B, and 27B.

    2.6Bhealth-ai-developer-foundations
    12.2KMar 2025gguf
    • Same category
    • Similar size (2.6B vs 3.7B)
    vs
  8. NousResearch logo

    Hermes-3-Llama-3.2-3B

    NousResearch·Chat

    ≈3.3 GB

    Hermes 3 3B is a small but mighty new addition to the Hermes series of LLMs by Nous Research, and is Nous's first fine-tune in this parameter class.

    3.2B128K ctx Llama 3 Community License
    4.5KDec 2024gguf
    • Same category
    • Similar size (3.2B vs 3.7B)
    vs
  9. arcee-ai logo

    AFM-4.5B-Base

    arcee-ai·Chat

    ≈3.8 GB

    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 2.0
    1.6KJul 2025gguf
    • Same category
    • Similar size (4.6B vs 3.7B)
    • Commercial use OK
    vs
  10. ibm-granite logo

    granite-4.1-8b

    ibm-granite·Chat

    ≈7.0 GB

    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 2.0
    82.2KApr 2026ollama
    • Same category
    • Larger (8.8B vs 3.7B)
    • Commercial use OK
    vs
  11. meta-llama logo

    Llama-3.1-8B-Instruct

    meta-llama·Chat

    ≈6.3 GB

    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 License
    4.2MJul 2024ollama
    • Same category
    • Larger (8B vs 3.7B)
    • Widely used
    vs
  12. Qwen logo

    Qwen3-8B-Base

    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.

    8.2B32K ctx Apache 2.0
    597.9KApr 2025gguf
    • Same category
    • Larger (8.2B vs 3.7B)
    • Commercial use OK
    vs
  13. Qwen logo≈1.6 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:

    1.5B32K ctx Apache 2.0
    5.1MSept 2024ollama
    • Same category
    • Smaller (1.5B vs 3.7B)
    • Commercial use OK
    • Widely used
    vs
  14. Salesforce logo

    xLAM-2-3b-fc-r

    Salesforce·Chat

    ≈2.6 GB

    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 4.0
    2.3KMar 2025gguf
    • Same category
    • Similar size (3.1B vs 3.7B)
    vs
  15. swiss-ai logo≈6.3 GB

    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 2.0
    204.9KAug 2025gguf
    • Same category
    • Larger (8.1B vs 3.7B)
    • Commercial use OK
    vs
  16. microsoft logo

    Sentiment-Analysis-7B

    microsoft·Chat

    ≈5.8 GB

    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 MIT
    3KOct 2026gguf
    • Same category
    • Similar size (7.2B vs 3.7B)
    • Commercial use OK
    • Newer release
    vs
  17. IFM logo

    K2-Horizon-7B

    IFM·Chat

    ≈7.0 GB

    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 2.0
    28.7KSept 2026gguf
    • Same category
    • Larger (9B vs 3.7B)
    • Commercial use OK
    vs
  18. nvidia logo≈6.6 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.

    8.5B256K ctx nvidia-nemotron-open-model-license
    60.5KMar 2026gguf
    • Same category
    • Larger (8.5B vs 3.7B)
    • Commercial use OK
    vs
  19. XHToken logo

    Spark-X2.6-1.7B

    XHToken·Chat

    ≈1.9 GB

    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 2.0
    5.6KOct 2026gguf
    • Same category
    • Smaller (1.7B vs 3.7B)
    • Commercial use OK
    • Newer release
    vs
  20. A compact 9B reasoning model distilled from DeepSeek-V4-Pro in Max Effect mode

    9.4B256K ctx Apache 2.0
    27KOct 2026gguf
    • Same category
    • Larger (9.4B vs 3.7B)
    • Commercial use OK
    • Newer release
    vs
  21. microsoft logo

    phi-2

    microsoft·Chat

    ≈2.8 GB

    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 MIT
    180.7KDec 2023gguf
    • Same category
    • Similar size (2.8B vs 3.7B)
    • Commercial use OK
    vs
  22. tiiuae logo

    Falcon3-3B-Base

    tiiuae·Chat

    ≈3.1 GB

    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 License
    2.6KDec 2024gguf
    • Same category
    • Similar size (3.2B vs 3.7B)
    vs
  23. ibm-granite logo

    granite-3.1-2b-instruct

    ibm-granite·Chat

    ≈2.6 GB

    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 2.0
    21.5KDec 2024gguf
    • Same category
    • Similar size (2.5B vs 3.7B)
    • Commercial use OK
    vs
  24. ibm-granite logo

    granite-4.0-h-tiny

    ibm-granite·Chat

    ≈5.2 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.

    6.9BA1.5B128K ctx Apache 2.0
    28.9KSept 2025gguf
    • Same category
    • Similar size (6.9B vs 3.7B)
    • Commercial use OK
    vs