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-X2.6-1.7B

120 open-weight models that do the same job as Spark-X2.6-1.7B (1.7B 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
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
--vram
any
--gpus
--quant
  1. Salesforce logo

    CoDA-v0-Instruct

    Salesforce·Chat

    ≈2.6 GB

    Welcome to CoDA, Salesforce AI Research's diffusion-based language model designed for powerful code generation and bidirectional context understanding, presented in the paper CoDA: Coding LM via Diffusion Adaptation.

    2B40K ctx CC BY-NC 4.0
    488Sept 2025
    • Same category
    • Similar size (2B vs 1.7B)
    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 1.7B)
    • Commercial use OK
    vs
  3. Qwen logo≈1.8 GB

    Qwen3Guard is a series of safety moderation models built upon Qwen3 and trained on a dataset of 1.19 million prompts and responses labeled for safety.

    752M32K ctx Apache 2.0
    157.6KSept 2025gguf
    • Same category
    • Smaller (752M vs 1.7B)
    • Commercial use OK
    vs
  4. WeiboAI logo

    VibeThinker-3B

    WeiboAI·Chat

    ≈2.6 GB

    2.For harder math reasoning, try AMOBench , a problem set harder than the International Mathematical Olympiad (IMO), with included standard answers. Use it to evaluate VibeThinker against other SOTA models. Note: due to extreme difficulty, set max tokens to 60K–100K.

    3.1B128K ctx MIT
    2.6KJun 2026gguf
    • Same category
    • Similar size (3.1B vs 1.7B)
    • Commercial use OK
    vs
  5. kyutai logo

    helium-1-2b

    kyutai·Chat

    ≈2.1 GB

    Helium-1 is a lightweight language model with 2B parameters, targeting edge and mobile devices. It supports the 24 official languages of the European Union.

    2B4K ctx CC BY-SA 4.0
    1.2KApr 2025gguf
    • Same category
    • Similar size (2B vs 1.7B)
    • Commercial use OK
    vs
  6. ai21labs logo

    AI21-Jamba2-3B

    ai21labs·Chat

    ≈2.4 GB

    Jamba2 3B is an ultra-compact open source model designed to bring enterprise-grade reliability to on-device deployments. At just 3B parameters, it runs efficiently on consumer devices—iPhones, Androids, Macs, and PCs—while maintaining the grounding and instruction-following capabilities required…

    3B256K ctx Apache 2.0
    6.6KJan 2026gguf
    • Same category
    • Similar size (3B vs 1.7B)
    • Commercial use OK
    vs
  7. 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 1.7B)
    • Commercial use OK
    vs
  8. jinaai logo

    ReaderLM-v2

    jinaai·Chat

    ≈1.6 GB

    ReaderLM-v2 is a 1.5B parameter language model that converts raw HTML into beautifully formatted markdown or JSON with superior accuracy and improved longer context handling.

    1.5B513K ctx CC BY-NC 4.0
    1.3KJan 2025ollama
    • Same category
    • Similar size (1.5B vs 1.7B)
    vs
  9. llm-jp logo

    llm-jp-3-1.8b

    llm-jp·Chat

    ≈2.4 GB

    This repository provides large language models developed by the Research and Development Center for Large Language Models at the National Institute of Informatics.

    1.9B4K ctx Apache 2.0
    2.6KSept 2024
    • Same category
    • Similar size (1.9B vs 1.7B)
    • Commercial use OK
    vs
  10. sbintuitions logo≈2.0 GB

    This repository provides Japanese language models trained by SB Intuitions.

    1.4B8K ctx MIT
    2KFeb 2025gguf
    • Same category
    • Similar size (1.4B vs 1.7B)
    • Commercial use OK
    vs
  11. 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 1.7B)
    • Commercial use OK
    vs
  12. 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 1.7B)
    vs
  13. google logo

    gemma-3-1b-pt

    google·Chat

    ≈1.3 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.

    1B32K ctx Gemma Terms of Use
    39.9KFeb 2025gguf
    • Same category
    • Similar size (1B vs 1.7B)
    vs
  14. 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 1.7B)
    vs
  15. manycore-research logo

    SpatialLM-Llama-1B

    manycore-research·Chat

    ≈1.5 GB

    SpatialLM is a 3D large language model designed to process 3D point cloud data and generate structured 3D scene understanding outputs. These outputs include architectural elements like walls, doors, windows, and oriented object bounding boxes with their semantic categories.

    1.2B128K ctx Llama 3.2 Community License
    4.7KMar 2025
    • Same category
    • Similar size (1.2B vs 1.7B)
    vs
  16. 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 1.7B)
    vs
  17. Qwen logo

    Qwen2.5-3B

    Qwen·Chat

    ≈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
    218.8KSept 2024gguf
    • Same category
    • Similar size (3.1B vs 1.7B)
    vs
  18. Qwen logo

    Qwen3-4B-Base

    Qwen·Chat

    ≈4.0 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.

    4B32K ctx Apache 2.0
    434.9KApr 2025gguf
    • Same category
    • Larger (4B vs 1.7B)
    • Commercial use OK
    vs
  19. internlm logo

    internlm2_5-1_8b-chat

    internlm·Chat

    ≈2.4 GB

    InternLM2.5 has open-sourced a 1.8 billion parameter base model and a chat model tailored for practical scenarios. The model has the following characteristics:

    1.9B32K ctx Custom licence
    3.4KJul 2024gguf
    • Same category
    • Similar size (1.9B vs 1.7B)
    vs
  20. LiquidAI logo

    LFM2-1.2B-RAG

    LiquidAI·Chat

    ≈1.4 GB

    Based on LFM2-1.2B, LFM2-1.2B-RAG is specialized in answering questions based on provided contextual documents, for use in RAG (Retrieval-Augmented Generation) systems.

    1.2B125K ctx lfm1.0
    2.1KSept 2025gguf
    • Same category
    • Similar size (1.2B vs 1.7B)
    vs
  21. microsoft logo

    phi-1_5

    microsoft·Chat

    ≈1.7 GB

    The language model Phi-1.5 is a Transformer with 1.3 billion parameters. It was trained using the same data sources as phi-1, augmented with a new data source that consists of various NLP synthetic texts.

    1.4B2K ctx MIT
    50.9KSept 2023gguf
    • Same category
    • Similar size (1.4B vs 1.7B)
    • Commercial use OK
    vs
  22. ibm-granite logo

    granite-3.1-1b-a400m-base

    ibm-granite·Chat

    ≈1.7 GB

    Model Summary: Granite-3.1-1B-A400M-Base extends the context length of Granite-3.0-1B-A400M-Base from 4K to 128K using a progressive training strategy by increasing the supported context length in increments while adjusting RoPE theta until the model has successfully adapted to desired length of…

    1.3BA400M128K ctx Apache 2.0
    4.4KDec 2024gguf
    • Same category
    • Similar size (1.3B vs 1.7B)
    • Commercial use OK
    vs
  23. openbmb logo

    MiniCPM-2B-sft-bf16

    openbmb·Chat

    ≈3.1 GB

    MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 2.4B parameters excluding embeddings.

    2B4K ctx Unknown licence
    20.8KJan 2024gguf
    • Same category
    • Similar size (2B vs 1.7B)
    vs
  24. kyutai logo≈2.7 GB

    Helium-1 preview is a lightweight language model with 2B parameters, targeting edge and mobile devices. It supports the following languages: English, French, German, Italian, Portuguese, Spanish.

    2.2B4K ctx CC BY 4.0
    3KJan 2025
    • Same category
    • Similar size (2.2B vs 1.7B)
    • Commercial use OK
    vs