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 Spark-X2.6-4B-Base

120 open-weight models that do the same job as Spark-X2.6-4B-Base (4.1B 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
XHToken logo

Spark-X2.6-4B-Base

XHToken·Chat

≈4.1 GB

A little over a month has passed since Spark-X2.5. In the rapidly evolving world of AI agents, that is enough time to rethink, refine, and move the frontier forward.

4.1B1M ctx Apache 2.0
2.5KOct 2026gguf
--vram
any
--gpus
--quant
  1. Qwen logo≈2.6 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:

    3.1B32K ctx Qwen Research License
    2MSept 2024ollama
    • Same category
    • Similar size (3.1B vs 4.1B)
    • Widely used
    vs
  2. ibm-granite logo

    granite-4.1-3b-base

    ibm-granite·Chat

    ≈3.1 GB

    Model Summary: Granite‑4.1‑3B‑Base is a decoder‑only language model with long‑context capabilities, designed to support a broad range of general text‑to‑text generation tasks, as well as fill‑in‑the‑Middle (FIM) code completion.

    3.4B128K ctx Apache 2.0
    10.6KApr 2026gguf
    • Same category
    • Similar size (3.4B vs 4.1B)
    • Commercial use OK
    vs
  3. 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 4.1B)
    • Commercial use OK
    vs
  4. 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 4.1B)
    • Commercial use OK
    vs
  5. microsoft logo

    Phi-3.5-mini-instruct

    microsoft·Chat

    ≈5.8 GB

    Phi-3.5-mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length.

    3.8B128K ctx MIT
    340.3KAug 2024gguf
    • Same category
    • Similar size (3.8B vs 4.1B)
    • Commercial use OK
    vs
  6. 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 4.1B)
    • Commercial use OK
    vs
  7. 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 4.1B)
    • Commercial use OK
    vs
  8. 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
    • Same category
    • Similar size (3.5B vs 4.1B)
    • Commercial use OK
    • Newer release
    vs
  9. 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 4.1B)
    vs
  10. microsoft logo

    Phi-tiny-MoE-instruct

    microsoft·Chat

    ≈3.0 GB

    Phi-tiny-MoE is a lightweight Mixture of Experts (MoE) model with 3.8B total parameters and 1.1B activated parameters. It is compressed and distilled from the base model shared by Phi-3.5-MoE and GRIN-MoE using the SlimMoE approach, then post-trained via supervised fine-tuning and direct preference…

    3.8BA1.3B4K ctx MIT
    30.3KJun 2025gguf
    • Same category
    • Similar size (3.8B vs 4.1B)
    • Commercial use OK
    vs
  11. 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 4.1B)
    • Commercial use OK
    vs
  12. meta-llama logo

    Llama-3.2-3B-Instruct

    meta-llama·Chat

    ≈3.3 GB

    The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out).

    3.2B128K ctx Llama 3.2 Community License
    834.2KSept 2024ollama
    • Same category
    • Similar size (3.2B vs 4.1B)
    vs
  13. 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 4.1B)
    • Commercial use OK
    vs
  14. 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 4.1B)
    • Commercial use OK
    vs
  15. ibm-granite logo

    granite-4.0-micro

    ibm-granite·Chat

    ≈3.1 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.

    3.4B128K ctx Apache 2.0
    22.2KSept 2025gguf
    • Same category
    • Similar size (3.4B vs 4.1B)
    • Commercial use OK
    vs
  16. 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
    • Similar size (8.2B vs 4.1B)
    • Commercial use OK
    • Widely used
    vs
  17. HuggingFaceTB logo

    SmolLM3-3B-Base

    HuggingFaceTB·Chat

    ≈2.9 GB

    SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports 6 languages, advanced reasoning and long context. SmolLM3 is a fully open model that offers strong performance at the 3B–4B scale.

    3.1B64K ctx Apache 2.0
    88.2KJun 2025gguf
    • Same category
    • Similar size (3.1B vs 4.1B)
    • Commercial use OK
    vs
  18. 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 4.1B)
    • Commercial use OK
    vs
  19. ornith-ai logo

    Ornith-1.5-9B

    ornith-ai·Chat

    ≈7.2 GB

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

    9.7B256K ctx MIT
    570.4KAug 2026ollama
    • Same category
    • Larger (9.7B vs 4.1B)
    • Commercial use OK
    vs
  20. CohereLabs logo

    tiny-aya-earth

    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
    6KFeb 2026gguf
    • Same category
    • Similar size (3.3B vs 4.1B)
    vs
  21. 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 4.1B)
    • Commercial use OK
    vs
  22. meta-llama logo

    Llama-3.2-3B

    meta-llama·Chat

    ≈3.3 GB

    The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out).

    3.2B128K ctx Llama 3.2 Community License
    313.5KSept 2024gguf
    • Same category
    • Similar size (3.2B vs 4.1B)
    vs
  23. openbmb logo

    MiniCPM5-2B-Base

    openbmb·Chat

    ≈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.

    2.5B512K ctx Apache 2.0
    12.8KAug 2026gguf
    • Same category
    • Similar size (2.5B vs 4.1B)
    • Commercial use OK
    vs
  24. 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 4.1B)
    • Commercial use OK
    vs