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. tiiuae logo

    Falcon3-1B-Base

    tiiuae·Chat

    ≈1.8 GB

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

    1.7B4K ctx Falcon LLM License
    4.1KDec 2024gguf
    • Same category
    • Similar size (1.7B vs 1.7B)
    vs
  2. google logo

    gemma-3-1b-it

    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
    203.3KMar 2025ollama
    • Same category
    • Similar size (1B vs 1.7B)
    vs
  3. ibm-granite logo

    granite-4.0-h-1b-base

    ibm-granite·Chat

    ≈2.0 GB

    Model Summary: Granite-4.0-H-1B-Base is a lightweight decoder-only language model designed for scenarios where efficiency and speed are critical. They can run on resource-constrained devices such as smartphones or IoT hardware, enabling offline and privacy-preserving applications.

    1.5B128K ctx Apache 2.0
    1.4KOct 2025gguf
    • Same category
    • Similar size (1.5B vs 1.7B)
    • Commercial use OK
    vs
  4. Nanbeige logo

    Nanbeige4.2-3B

    Nanbeige·Chat

    ≈3.7 GB

    Nanbeige4.2-3B is a compact agentic model built on Nanbeige4.2-3B-Base, designed to combine strong agentic behavior with broad reasoning and alignment capabilities. Its Looped Transformer architecture reuses the transformer layers to increase model capacity without adding parameters.

    4.2B256K ctx Apache 2.0
    89.1KJul 2026gguf
    • Same category
    • Larger (4.2B vs 1.7B)
    • Commercial use OK
    vs
  5. ByteDance logo

    Ouro-2.6B

    ByteDance·Chat

    ≈5.1 GB

    Ouro-2.6B is a 2.6 billion parameter Looped Language Model (LoopLM) that achieves exceptional parameter efficiency through iterative shared-weight computation.

    2.7B64K ctx Apache 2.0
    10.3KOct 2025gguf
    • Same category
    • Similar size (2.7B vs 1.7B)
    • Commercial use OK
    vs
  6. LiquidAI logo

    LFM2-1.2B

    LiquidAI·Chat

    ≈1.4 GB

    LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

    1.2B125K ctx lfm1.0
    15.6KJul 2025gguf
    • Same category
    • Similar size (1.2B vs 1.7B)
    vs
  7. 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 1.7B)
    • Commercial use OK
    vs
  8. meta-llama logo

    Llama-Guard-3-1B

    meta-llama·Chat

    ≈1.8 GB

    Llama Guard 3-1B is a fine-tuned Llama-3.2-1B pretrained model for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification).

    1.5BLlama 3.2 Community License
    14.2KSept 2024ollama
    • Same category
    • Similar size (1.5B vs 1.7B)
    vs
  9. XHToken logo

    Spark-X2.6-4B

    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
    30.8KOct 2026gguf
    • Same category
    • Larger (4.1B vs 1.7B)
    • Commercial use OK
    vs
  10. CohereLabs logo

    tiny-aya-global

    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
    28.8KFeb 2026gguf
    • Same category
    • Similar size (3.3B vs 1.7B)
    vs
  11. nvidia logo≈3.6 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.

    3.8B256K ctx nvidia-nemotron-open-model-license
    81.1KMar 2026gguf
    • Same category
    • Larger (3.8B vs 1.7B)
    • Commercial use OK
    vs
  12. LiquidAI logo

    LFM2-2.6B

    LiquidAI·Chat

    ≈2.5 GB

    LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

    2.6B125K ctx lfm1.0
    6.6KSept 2025gguf
    • Same category
    • Similar size (2.6B vs 1.7B)
    vs
  13. LiquidAI logo

    LFM2.5-1.2B-JP

    LiquidAI·Chat

    ≈1.4 GB

    LFM2.5-1.2B-JP is a chat model specifically optimized for Japanese. While LFM2 already supported Japanese as one of eight languages, LFM2.5-JP pushes state-of-the-art on Japanese knowledge and instruction-following at its scale.

    1.2B125K ctx lfm1.0
    2.9KJan 2026gguf
    • Same category
    • Similar size (1.2B vs 1.7B)
    vs
  14. 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 1.7B)
    vs
  15. ibm-granite logo

    granite-swash-3b-a600m

    ibm-granite·Chat

    ≈2.5 GB

    Model Summary Granite-SWASH-3B-a600M is a 3B parameter decoder-only sparse language model with per-layer Sliding Window Attention (SWA) and learnable attention sinks (LSE-based).

    3BA600M8K ctx Apache 2.0
    3KJul 2026gguf
    • Same category
    • Similar size (3B vs 1.7B)
    • Commercial use OK
    vs
  16. NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16 is a looped (latent-recurrent) large language model (LLM) trained by NVIDIA. The model employs a normalized-GPT architecture with interleaved hybrid sliding window attention (SWA) and full attention layers.

    4B256K ctx openmdw-1.1
    16.2KOct 2026gguf
    • Same category
    • Larger (4B vs 1.7B)
    • Commercial use OK
    vs
  17. empero-ai logo

    Qwen3.8-4B-Distill

    empero-ai·Chat

    ≈4.3 GB

    Qwen3.8-4B is a full-parameter distillation of Qwen3.8 2.4T A95B into the Qwen3.5-4B architecture. The student was trained on ~45,000 curated teacher traces from our internal Qwen3.8 distillation datasets — dense chain-of-thought spanning mathematics, general reasoning, and instruction following…

    4.7B256K ctx Apache 2.0
    112.4KAug 2026gguf
    • Same category
    • Larger (4.7B vs 1.7B)
    • Commercial use OK
    vs
  18. google logo

    gemma-2-2b-it

    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
    183.2KJul 2024ollama
    • Same category
    • Similar size (2.6B vs 1.7B)
    vs
  19. EleutherAI logo

    pythia-1.4b

    EleutherAI·Chat

    ≈1.8 GB

    The Pythia Scaling Suite is a collection of models developed to facilitate interpretability research (see paper). It contains two sets of eight models of sizes 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B.

    1.5B2K ctx Apache 2.0
    77KFeb 2023gguf
    • Same category
    • Similar size (1.5B vs 1.7B)
    • Commercial use OK
    vs
  20. LiquidAI logo

    LFM2-2.6B-Exp

    LiquidAI·Chat

    ≈2.5 GB

    LFM2-2.6B-Exp is an experimental checkpoint built on LFM2-2.6B using pure reinforcement learning.

    2.6B125K ctx lfm1.0
    2.4KDec 2025gguf
    • Same category
    • Similar size (2.6B vs 1.7B)
    vs
  21. m-a-p logo≈3.7 GB

    --- Our model's name is YuE (乐). In Chinese, the word means "music" and "happiness." Some of you may find words that start with Yu hard to pronounce. If so, you can just call it "yeah." We wrote a song with our model's name.

    2B8K ctx Apache 2.0
    2.6KJan 2025gguf
    • Same category
    • Similar size (2B vs 1.7B)
    • Commercial use OK
    vs
  22. openbmb logo

    BitCPM-CANN-3B

    openbmb·Chat

    ≈2.5 GB

    BitCPM-CANN is the first end-to-end 1.58-bit (ternary) large language model training system natively built on Huawei Ascend NPU.

    3B32K ctx Apache 2.0
    3KMay 2026gguf
    • Same category
    • Similar size (3B vs 1.7B)
    • Commercial use OK
    vs
  23. 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
  24. TinyLlama logo≈1.2 GB

    The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.

    1.1B2K ctx Apache 2.0
    923KDec 2023ollama
    • Same category
    • Similar size (1.1B vs 1.7B)
    • Commercial use OK
    vs