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 LFM3-1.7B

120 open-weight models that do the same job as LFM3-1.7B (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
LiquidAI logo

LFM3-1.7B

LiquidAI·Chat

≈1.9 GB

LFM3-1.7B is a text model for local agents and specialized applications, based on our new tri-hybrid architecture.

1.7B256K ctx lfm1.0
103.7KOct 2026ollama
--vram
any
--gpus
--quant
  1. tencent logo

    Youtu-LLM-2B-Base

    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
    1.1KDec 2025gguf
    • Same category
    • Similar size (2B vs 1.7B)
    vs
  2. 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
  3. HuggingFaceTB logo

    SmolLM3-3B

    HuggingFaceTB·Chat

    ≈2.9 GB

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

    3.1B64K ctx Apache 2.0
    229.1KJul 2025gguf
    • Same category
    • Similar size (3.1B vs 1.7B)
    • Commercial use OK
    vs
  4. lightonai logo

    colgrep-agent-2B

    lightonai·Chat

    ≈2.3 GB

    ColGrep-Agent-2B is a lightweight code-localization agent designed to identify the files and line ranges relevant to a GitHub issue, bug report, feature request, or natural-language question about a repository.

    2.5B128K ctx Apache 2.0
    1.1KOct 2026gguf
    • Same category
    • Similar size (2.5B vs 1.7B)
    • Commercial use OK
    vs
  5. openbmb logo

    MiniCPM5-1B-SFT

    openbmb·Chat

    ≈1.3 GB

    We are releasing MiniCPM5-1B, the first model in the MiniCPM5 series. It is a dense 1B Transformer built for on-device, local deployment, and resource-constrained scenarios, reaching 1B-class open-source SOTA.

    1.1B128K ctx Apache 2.0
    6.9KMay 2026gguf
    • Same category
    • Similar size (1.1B vs 1.7B)
    • Commercial use OK
    vs
  6. 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 1.7B)
    • Widely used
    vs
  7. sapientinc logo

    HRM-Text-1B

    sapientinc·Chat

    ≈1.6 GB

    A 1 B-parameter language model checkpoint built on the Hierarchical Reasoning Model (HRM) architecture, trained by Sapient Intelligence from scratch on structured public datasets.

    1.2B4K ctx Apache 2.0
    3.3KMay 2026gguf
    • Same category
    • Similar size (1.2B vs 1.7B)
    • Commercial use OK
    vs
  8. tiiuae logo≈1.9 GB

    For more details about the training protocol of this model, please refer to the Falcon-H1 technical blogpost and Technical Report.

    1.6B128K ctx Falcon LLM License
    4.7KMay 2025gguf
    • Same category
    • Similar size (1.6B vs 1.7B)
    vs
  9. utter-project logo

    EuroLLM-1.7B-Instruct

    utter-project·Chat

    ≈1.9 GB

    This is the model card for the first instruction tuned model of the EuroLLM series: EuroLLM-1.7B-Instruct. You can also check the pre-trained version: EuroLLM-1.7B.

    1.7B4K ctx Apache 2.0
    19.9KAug 2024gguf
    • Same category
    • Similar size (1.7B vs 1.7B)
    • Commercial use OK
    vs
  10. paradigma-inc logo

    limite-1b-violetto

    paradigma-inc·Chat

    ≈1.5 GB

    Limite 1B - Violetto is Paradigma’s first model, designed for high-throughput solutions of difficult mathematical problems.

    1B128K ctx Apache 2.0
    3.7KSept 2026gguf
    • Same category
    • Similar size (1B vs 1.7B)
    • Commercial use OK
    vs
  11. ibm-granite logo

    granite-4.2-3b

    ibm-granite·Chat

    ≈3.3 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.

    3.7B128K ctx Apache 2.0
    40.8KAug 2026ollama
    • Same category
    • Larger (3.7B vs 1.7B)
    • Commercial use OK
    vs
  12. LiquidAI logo

    LFM2.5-1.2B-Base

    LiquidAI·Chat

    ≈1.4 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.

    1.2B125K ctx Custom licence
    7.5KJan 2026gguf
    • Same category
    • Similar size (1.2B vs 1.7B)
    vs
  13. llm-jp logo≈2.4 GB

    LLM-jp-3.1 is a series of 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
    2.5KMay 2025gguf
    • Same category
    • Similar size (1.9B vs 1.7B)
    • Commercial use OK
    vs
  14. Qwen logo

    Qwen3-4B

    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.

    4B40K ctx Apache 2.0
    3.1MApr 2025ollama
    • Same category
    • Larger (4B vs 1.7B)
    • Commercial use OK
    • Widely used
    vs
  15. RWKV logo≈2.9 GB

    This is an official BlinkDL release of RWKV-7 Goose in Hugging Face Transformers format. RWKV-7 is an attention-free recurrent architecture with a constant-size recurrent state and constant inference work per generated token. Training remains parallelizable.

    1.5BApache 2.0
    136Aug 2026
    • Same category
    • Similar size (1.5B vs 1.7B)
    • Commercial use OK
    vs
  16. tiiuae logo≈1.6 GB

    Falcon-H1 is a new series of large language models (LLMs) featuring hybrid architecture designs optimized for both high performance and efficiency across diverse use cases.

    1.6B128K ctx Falcon LLM License
    3.8KMay 2025gguf
    • Same category
    • Similar size (1.6B vs 1.7B)
    vs
  17. LGAI-EXAONE logo

    EXAONE-4.0-1.2B

    LGAI-EXAONE·Chat

    ≈1.7 GB

    🎉 License Updated! We are pleased to announce our more flexible licensing terms 🤗 ✈️ Try on FriendliAI (licensed under commercial purposes) 📢 EXAONE 4.0 is officially supported by HuggingFace transformers! Please check out the guide below

    1.3B64K ctx exaone
    11.8KJul 2025gguf
    • Same category
    • Similar size (1.3B vs 1.7B)
    vs
  18. utter-project logo

    EuroLLM-1.7B

    utter-project·Chat

    ≈1.9 GB

    This is the model card for the first pre-trained model of the EuroLLM series: EuroLLM-1.7B. You can also check the instruction tuned version: EuroLLM-1.7B-Instruct.

    1.7B4K ctx Apache 2.0
    11.3KAug 2024gguf
    • Same category
    • Similar size (1.7B vs 1.7B)
    • Commercial use OK
    vs
  19. 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 1.7B)
    vs
  20. openbmb logo≈2.5 GB

    This is the RL initialization checkpoint used in the blog JustRL II: Scaling Small LLMs to 128K Reasoning with a Critic (中文版).

    2.8B64K ctx Unknown licence
    2.2KSept 2026
    • Same category
    • Similar size (2.8B vs 1.7B)
    vs
  21. openbmb logo

    MiniCPM5-1B-Base

    openbmb·Chat

    ≈1.3 GB

    We are releasing MiniCPM5-1B, the first model in the MiniCPM5 series. It is a dense 1B Transformer built for on-device, local deployment, and resource-constrained scenarios, reaching 1B-class open-source SOTA.

    1.1B128K ctx Apache 2.0
    4.3KMay 2026gguf
    • Same category
    • Similar size (1.1B vs 1.7B)
    • Commercial use OK
    vs
  22. ibm-granite logo

    granite-3.3-2b-instruct

    ibm-granite·Chat

    ≈2.6 GB

    Model Summary: Granite-3.3-2B-Instruct is a 2-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities.

    2.5B128K ctx Apache 2.0
    40.8KApr 2025ollama
    • Same category
    • Similar size (2.5B vs 1.7B)
    • Commercial use OK
    vs
  23. LiquidAI logo

    LFM2-2.6B-Longevity

    LiquidAI·Chat

    ≈2.5 GB

    Longevity-LLM (L-LLM) is a family of compact, domain-adapted language models for interpreting heterogeneous aging biology data. Longevity LFMs are available in two sizes:

    2.6B125K ctx lfm1.0
    2.1KMay 2026gguf
    • Same category
    • Similar size (2.6B vs 1.7B)
    vs
  24. Salesforce logo

    xLAM-2-1b-fc-r

    Salesforce·Chat

    ≈1.6 GB

    Large Action Models (LAMs) are advanced language models designed to enhance decision-making by translating user intentions into executable actions.

    1.5B32K ctx CC BY-NC 4.0
    3.9KMar 2025gguf
    • Same category
    • Similar size (1.5B vs 1.7B)
    vs