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. Qwen logo≈1.5 GB

    In August 2024, we released the first series of mathematical LLMs - Qwen2-Math - of our Qwen family. A month later, we have upgraded it and open-sourced Qwen2.5-Math series, including base models Qwen2.5-Math-1.5B/7B/72B, instruction-tuned models Qwen2.5-Math-1.5B/7B/72B-Instruct, and mathematical…

    1.5B4K ctx Apache 2.0
    159.3KSept 2024gguf
    • Same category
    • Similar size (1.5B vs 1.7B)
    • Commercial use OK
    vs
  2. HuggingFaceTB logo

    SmolLM2-1.7B

    HuggingFaceTB·Chat

    ≈3.0 GB

    The 1.7B variant demonstrates significant advances over its predecessor SmolLM1-1.7B, particularly in instruction following, knowledge, reasoning, and mathematics.

    1.7B8K ctx Apache 2.0
    42.4KOct 2024ollama
    • Same category
    • Similar size (1.7B vs 1.7B)
    • Commercial use OK
    vs
  3. Qwen logo

    Qwen3-0.6B

    Qwen·Chat

    ≈1.8 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.

    752M40K ctx Apache 2.0
    17.8MApr 2025ollama
    • Same category
    • Smaller (752M vs 1.7B)
    • Commercial use OK
    • Widely used
    vs
  4. nvidia logo≈4.2 GB

    NVIDIA-Nemotron-3-Nano-4B-BF16 is a small language model (SLM) 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.

    4B256K ctx nvidia-nemotron-open-model-license
    1.9MMar 2026gguf
    • Same category
    • Larger (4B vs 1.7B)
    • Commercial use OK
    • Widely used
    vs
  5. IFM logo≈1.6 GB

    K2-Horizon-0.9B is the compact dense member of the K2-Horizon family: a 0.9B-class decoder-only model with a 128K context window.

    1.1B128K ctx Apache 2.0
    11.9KSept 2026gguf
    • Same category
    • Similar size (1.1B vs 1.7B)
    • Commercial use OK
    vs
  6. openbmb logo

    MiniCPM5-2B-SFT

    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.

    2.5B128K ctx Apache 2.0
    6.6KAug 2026
    • Same category
    • Similar size (2.5B vs 1.7B)
    • Commercial use OK
    vs
  7. Qwen logo≈1.5 GB

    In August 2024, we released the first series of mathematical LLMs - Qwen2-Math - of our Qwen family. A month later, we have upgraded it and open-sourced Qwen2.5-Math series, including base models Qwen2.5-Math-1.5B/7B/72B, instruction-tuned models Qwen2.5-Math-1.5B/7B/72B-Instruct, and mathematical…

    1.5B4K ctx Apache 2.0
    101.2KSept 2024gguf
    • Same category
    • Similar size (1.5B vs 1.7B)
    • Commercial use OK
    vs
  8. tencent logo

    Youtu-LLM-2B

    tencent·Chat

    ≈4.7 GB

    Youtu-LLM is a new, small, yet powerful LLM, contains only 1.96B parameters, supports 128k long context, and has native agentic talents.

    2B128K ctx youtu-llm
    3.9KDec 2025gguf
    • Same category
    • Similar size (2B vs 1.7B)
    vs
  9. meta-llama logo

    Llama-3.2-1B

    meta-llama·Chat

    ≈1.5 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).

    1.2B128K ctx Llama 3.2 Community License
    643.8KSept 2024gguf
    • Same category
    • Similar size (1.2B vs 1.7B)
    vs
  10. openbmb logo≈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.

    2.5B128K ctx Apache 2.0
    4.8KSept 2026
    • Same category
    • Similar size (2.5B vs 1.7B)
    • Commercial use OK
    vs
  11. WeiboAI logo

    VibeThinker-1.5B

    WeiboAI·Chat

    ≈1.8 GB

    VibeThinker-1.5B is a 1.5-billion parameter dense language model. With a total training cost of only $7,800 USD, it achieves reasoning performance comparable to larger models like GPT OSS-20B Medium.

    1.8B128K ctx MIT
    1.9KNov 2025gguf
    • Same category
    • Similar size (1.8B vs 1.7B)
    • Commercial use OK
    vs
  12. nvidia logo≈2.2 GB

    We're excited to introduce Nemotron-Labs-Audex-2B, a unified audio-text LLM with a similar recipe as Nemotron-Labs-Audex-30B-A3B. Audex-2B extends the vocabulary for discrete audio tokens used for speech and general audio outputs, as well as an audio encoder for speech and general audio inputs.

    2Bnvidia-oneway-noncommercial-license
    792Jul 2026
    • Same category
    • Similar size (2B vs 1.7B)
    vs
  13. Zyphra logo

    ZR1-1.5B

    Zyphra·Chat

    ≈1.8 GB

    ZR1-1.5B is a small reasoning model trained extensively on both verified coding and mathematics problems with reinforcement learning.

    1.8B128K ctx MIT
    8.4KApr 2025gguf
    • Same category
    • Similar size (1.8B vs 1.7B)
    • Commercial use OK
    vs
  14. LiquidAI logo

    LFM2.5-2.6B-Base

    LiquidAI·Chat

    ≈2.6 GB

    LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.

    2.7B125K ctx lfm1.0
    7.4KAug 2026gguf
    • Same category
    • Similar size (2.7B vs 1.7B)
    vs
  15. ibm-granite logo

    granite-4.0-h-1b

    ibm-granite·Chat

    ≈2.0 GB

    Model Summary: Granite-4.0-H-1B is a lightweight instruct model finetuned from Granite-4.0-H-1B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.

    1.5B128K ctx Apache 2.0
    4.2KOct 2025gguf
    • Same category
    • Similar size (1.5B vs 1.7B)
    • Commercial use OK
    vs
  16. Qwen logo

    Qwen2-1.5B

    Qwen·Chat

    ≈1.6 GB

    Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the 1.5B Qwen2 base language model.

    1.5B128K ctx Apache 2.0
    101.4KMay 2024gguf
    • Same category
    • Similar size (1.5B vs 1.7B)
    • Commercial use OK
    vs
  17. tencent logo≈2.1 GB

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

    1.8B256K ctx Unknown licence
    2.5KJul 2025gguf
    • Same category
    • Similar size (1.8B vs 1.7B)
    vs
  18. allenai logo

    Bolmo-1B

    allenai·Chat

    ≈1.9 GB

    OLMo 2 1B retrofitted to operate over bytes instead of tokens via byteification through a short additional training procedure.

    1.5B4K ctx Apache 2.0
    1.9KDec 2025
    • Same category
    • Similar size (1.5B vs 1.7B)
    • Commercial use OK
    vs
  19. HuggingFaceTB logo

    SmolLM-1.7B

    HuggingFaceTB·Chat

    ≈1.9 GB

    SmolLM is a series of state-of-the-art small language models available in three sizes: 135M, 360M, and 1.7B parameters. These models are built on Cosmo-Corpus, a meticulously curated high-quality training dataset.

    1.7B2K ctx Apache 2.0
    24.7KJul 2024ollama
    • Same category
    • Similar size (1.7B vs 1.7B)
    • Commercial use OK
    vs
  20. Qwen logo≈1.6 GB

    Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 1.5B Qwen2 model.

    1.5B32K ctx Apache 2.0
    80.9KJun 2024ollama
    • Same category
    • Similar size (1.5B vs 1.7B)
    • Commercial use OK
    vs
  21. LiquidAI logo

    LFM2.5-1.2B-JP-202606

    LiquidAI·Chat

    ≈1.4 GB

    LFM2.5-1.2B-JP-202606 is our latest general purpose Japanese chat model, delivering significant improvements in knowledge, instruction following, math, code, and tool-use over both the models of comparable size and LFM2.5-1.2B-JP.

    1.2B125K ctx lfm1.0
    3.9KMay 2026gguf
    • Same category
    • Similar size (1.2B vs 1.7B)
    vs
  22. Qwen logo≈4.0 GB

    We introduce the updated version of the Qwen3-4B non-thinking mode, named Qwen3-4B-Instruct-2507, featuring the following key enhancements:

    4B256K ctx Apache 2.0
    2.7MAug 2025gguf
    • Same category
    • Larger (4B vs 1.7B)
    • Commercial use OK
    • Widely used
    vs
  23. tiiuae logo≈2.0 GB

    Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters.

    1.7B8K ctx Falcon LLM License
    9KDec 2024ollama
    • Same category
    • Similar size (1.7B vs 1.7B)
    vs
  24. Qwen logo≈3.1 GB

    Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include:

    1.8B32K ctx Qwen Research License
    145KJan 2024gguf
    • Same category
    • Similar size (1.8B vs 1.7B)
    vs