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 Crowd-v1

120 open-weight models that do the same job as Crowd-v1 (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
Vxtzq logo

Crowd-v1

Vxtzq·Chat

≈1.4 GB

Crowd-v1 is the first official model architecture released for CrowdGPT, a community-driven distributed AI project.

1BMIT
91KAug 2026
--vram
any
--gpus
--quant
  1. 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 1B)
    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 1B)
    • Commercial use OK
    vs
  3. openbmb logo

    MiniCPM-1B-sft-bf16

    openbmb·Chat

    ≈1.5 GB

    MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 1.2B parameters excluding embeddings.

    1B4K ctx Unknown licence
    1.5KApr 2024
    • Same category
    • Similar size (1B vs 1B)
    vs
  4. pfnet logo

    plamo-2-1b

    pfnet·Chat

    ≈1.3 GB

    PLaMo 2 1B is a 1B model pre-trained on English and Japanese datasets, developed by Preferred Elements, Inc.

    1.3B10M ctx Apache 2.0
    1.6KFeb 2025gguf
    • Same category
    • Similar size (1.3B vs 1B)
    • Commercial use OK
    vs
  5. 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 1B)
    • Commercial use OK
    • Widely used
    vs
  6. ibm-granite logo≈1.5 GB

    Model Summary: Granite-3.0-1B-A400M-Instruct is an 1B parameter model finetuned from Granite-3.0-1B-A400M-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.

    1.3BA400M4K ctx Apache 2.0
    4.6KOct 2024gguf
    • Same category
    • Similar size (1.3B vs 1B)
    • Commercial use OK
    vs
  7. 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 1B)
    vs
  8. 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 1B)
    vs
  9. amd logo

    AMD-OLMo-1B

    amd·Chat

    ≈1.4 GB

    AMD-OLMo are a series of 1B language models trained from scratch by AMD on AMD Instinct™ MI250 GPUs. The training code used is based on OLMo. We release the pre-trained model, supervised fine-tuned model, and DPO aligned model as follows:

    1.2B2K ctx Apache 2.0
    1.1KOct 2024gguf
    • Same category
    • Similar size (1.2B vs 1B)
    • Commercial use OK
    vs
  10. h2oai logo≈1.2 GB

    h2o-danube3-500m-chat is a chat fine-tuned model by H2O.ai with 500 million parameters. We release two versions of this model:

    514M8K ctx Apache 2.0
    266.5KJul 2024gguf
    • Same category
    • Similar size (514M vs 1B)
    • Commercial use OK
    vs
  11. 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
    • Larger (2.5B vs 1B)
    • Commercial use OK
    • Newer release
    vs
  12. Salesforce logo

    xLAM-1b-fc-r

    Salesforce·Chat

    ≈2.8 GB

    Welcome to the xLAM model family! Large Action Models (LAMs) are advanced large language models designed to enhance decision-making and translate user intentions into executable actions that interact with the world.

    1.3B16K ctx CC BY-NC 4.0
    8.6KJul 2024gguf
    • Same category
    • Similar size (1.3B vs 1B)
    vs
  13. 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 1B)
    vs
  14. 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 1B)
    • Commercial use OK
    vs
  15. 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 1B)
    vs
  16. 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
    • Larger (2.5B vs 1B)
    • Commercial use OK
    • Newer release
    vs
  17. 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 1B)
    • Commercial use OK
    vs
  18. allenai logo

    OLMo-1B-0724-hf

    allenai·Chat

    ≈1.8 GB

    OLMo 1B July 2024 is the latest version of the original OLMo 1B model rocking a 4.4 point increase in HellaSwag, among other evaluations improvements, from an improved version of the Dolma dataset and staged training. This version is for direct use with HuggingFace Transformers from v4.40 on.

    1.3B4K ctx Apache 2.0
    4.3KJun 2024gguf
    • Same category
    • Similar size (1.3B vs 1B)
    • Commercial use OK
    vs
  19. 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 1B)
    vs
  20. 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 1B)
    • Commercial use OK
    vs
  21. 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 1B)
    • Commercial use OK
    vs
  22. apple logo≈1.2 GB

    We introduce OpenELM, a family of Open Efficient Language Models. OpenELM uses a layer-wise scaling strategy to efficiently allocate parameters within each layer of the transformer model, leading to enhanced accuracy. We pretrained OpenELM models using the CoreNet library.

    1.1B2K ctx Apple Machine Learning Research License
    1.3KApr 2024gguf
    • Same category
    • Similar size (1.1B vs 1B)
    vs
  23. 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 1B)
    • Commercial use OK
    vs
  24. 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
    • Larger (2.7B vs 1B)
    vs