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 UserLM-2.0

120 open-weight models that do the same job as UserLM-2.0 (8B 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
microsoft logo

UserLM-2.0

microsoft·Chat

≈6.3 GB

UserLM-2.0 is an 8-billion-parameter user simulator for user-AI conversations. Unlike typical language models trained to play the assistant, UserLM-2.0 generates the user side of a conversation. It is conditioned on a task intent that describes the user's high-level objective.

8B128K ctx MIT
1.1KOct 2026gguf
--vram
any
--gpus
--quant
  1. meta-llama logo

    Meta-Llama-3-8B

    meta-llama·Chat

    ≈6.3 GB

    Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes.

    8B8K ctx Llama 3 Community License
    101.3KApr 2024gguf
    • Same category
    • Similar size (8B vs 8B)
    vs
  2. 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
    • Similar size (4B vs 8B)
    • Commercial use OK
    • Widely used
    vs
  3. tencent logo

    Hunyuan-7B-Instruct

    tencent·Chat

    ≈6.0 GB

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

    7.5B32K ctx Unknown licence
    5.4KJul 2025gguf
    • Same category
    • Similar size (7.5B vs 8B)
    vs
  4. nvidia logo≈6.5 GB

    We're excited to introduce Nemotron-Cascade-8B, a powerful general-purpose model trained through sequential and domain-wise reinforcement learning. Nemotron-Cascade-8B is post-trained from the Qwen3-8B-Base model.

    8.2B32K ctx NVIDIA Open Model License
    1.1KDec 2025gguf
    • Same category
    • Similar size (8.2B vs 8B)
    • Commercial use OK
    vs
  5. BSC-LT logo≈6.1 GB

    This repository contains the model described in Salamandra Technical Report.

    7.8B8K ctx Apache 2.0
    33.7KSept 2024gguf
    • Same category
    • Similar size (7.8B vs 8B)
    • Commercial use OK
    vs
  6. meta-llama logo

    Llama-Guard-3-8B

    meta-llama·Chat

    ≈6.3 GB

    Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned 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).

    8BLlama 3.1 Community License
    42.1KJul 2024ollama
    • Same category
    • Similar size (8B vs 8B)
    vs
  7. tencent logo

    HiLS-Attention-7B

    tencent·Chat

    ≈8.8 GB

    HiLS-Attention is a chunk-wise sparse attention mechanism that learns chunk selection end-to-end under the language-modeling loss, enabling native sparse training for efficient long-context modeling. This repository hosts the 7B checkpoint continued-trained on top of an OLMo3-style backbone.

    7.3B128K ctx Apache 2.0
    416Jul 2026
    • Same category
    • Similar size (7.3B vs 8B)
    • Commercial use OK
    vs
  8. ibm-granite logo

    granite-guardian-3.3-8b

    ibm-granite·Chat

    ≈6.6 GB

    Model Summary: Granite Guardian 3.3 8b is a specialized Granite 3.3 8B model designed to judge if the input prompts and the output responses of an LLM based system meet specified criteria.

    8.2B128K ctx Apache 2.0
    4.1KJun 2025gguf
    • Same category
    • Similar size (8.2B vs 8B)
    • Commercial use OK
    vs
  9. NousResearch logo

    Meta-Llama-3.1-8B

    NousResearch·Chat

    ≈6.3 GB

    The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out).

    8B128K ctx Llama 3.1 Community License
    38.1KJul 2024gguf
    • Same category
    • Similar size (8B vs 8B)
    vs
  10. zai-org logo

    GLM-4-9B-0414

    zai-org·Chat

    ≈6.4 GB

    The GLM family welcomes new members, the GLM-4-32B-0414 series models, featuring 32 billion parameters. Its performance is comparable to OpenAI’s GPT series and DeepSeek’s V3/R1 series. It also supports very user-friendly local deployment features.

    9.4B32K ctx MIT
    22.2KApr 2025ollama
    • Same category
    • Similar size (9.4B vs 8B)
    • Commercial use OK
    vs
  11. 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
    • Similar size (4.1B vs 8B)
    • Commercial use OK
    • Newer release
    vs
  12. allenai logo≈5.1 GB

    OLMoE-1B-7B-0125-Instruct January 2025 is post-trained variant of the OLMoE-1B-7B January 2025 model, which has undergone supervised finetuning on an OLMo-specific variant of the Tülu 3 dataset and further DPO training on this dataset, and finally RLVR training using this data.

    6.9BA1.3B4K ctx Apache 2.0
    32.7KJan 2025gguf
    • Same category
    • Similar size (6.9B vs 8B)
    • Commercial use OK
    vs
  13. speakleash logo≈5.9 GB

    Bielik-Minitron-7B-v3.0-Instruct is a generative text model featuring 7.35 billion parameters. It is an instruct-aligned version of the pruned Bielik-11B-v3-Base-20250730 model.

    7.5BApache 2.0
    905Jan 2026gguf
    • Same category
    • Similar size (7.5B vs 8B)
    • Commercial use OK
    vs
  14. google logo

    gemma-2-9b-it

    google·Chat

    ≈8.6 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.

    9.2B8K ctx Gemma Terms of Use
    130.7KJun 2024ollama
    • Same category
    • Similar size (9.2B vs 8B)
    vs
  15. ServiceNow-AI logo

    AprielGuard

    ServiceNow-AI·Chat

    ≈5.9 GB

    AprielGuard is an 8B parameter safeguard model designed to detect and mitigate both safety risks (e.g., toxicity, bias, misinformation) and security threats (e.g., prompt injections, jailbreaks, indirect prompt attacks) in large language model (LLM) interactions.

    7.9B128K ctx MIT
    829Nov 2025gguf
    • Same category
    • Similar size (7.9B vs 8B)
    • Commercial use OK
    vs
  16. tencent logo

    WeDLM-8B-Instruct

    tencent·Chat

    ≈6.5 GB

    WeDLM-8B-Instruct is our flagship instruction-tuned diffusion language model that performs parallel decoding under standard causal attention, fine-tuned from WeDLM-8B.

    8.2B16K ctx Apache 2.0
    657Dec 2025gguf
    • Same category
    • Similar size (8.2B vs 8B)
    • Commercial use OK
    vs
  17. ibm-granite logo

    granite-3.3-8b-base

    ibm-granite·Chat

    ≈6.6 GB

    Granite-3.3-8B-Base is a decoder-only language model with a 128K token context window. It improves upon Granite-3.1-8B-Base by adding support for Fill-in-the-Middle (FIM) using specialized tokens, enabling the model to generate content conditioned on both prefix and suffix.

    8.2B128K ctx Apache 2.0
    4.5KApr 2025gguf
    • Same category
    • Similar size (8.2B vs 8B)
    • Commercial use OK
    vs
  18. microsoft logo

    Phi-mini-MoE-instruct

    microsoft·Chat

    ≈5.5 GB

    Phi-mini-MoE is a lightweight Mixture of Experts (MoE) model with 7.6B total parameters and 2.4B activated parameters. It is compressed and distilled from the base model shared by Phi-3.5-MoE and GRIN-MoE using the SlimMoE approach, then post-trained via supervised fine-tuning and direct preference…

    7.6BA2.4B4K ctx MIT
    3.2KJun 2025gguf
    • Same category
    • Similar size (7.6B vs 8B)
    • Commercial use OK
    vs
  19. mistralai logo

    Mistral-7B-v0.1

    mistralai·Chat

    ≈5.8 GB

    The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested.

    7.2B32K ctx Apache 2.0
    445.4KSept 2023gguf
    • Same category
    • Similar size (7.2B vs 8B)
    • Commercial use OK
    vs
  20. EssentialAI logo

    rnj-1

    EssentialAI·Chat

    ≈6.4 GB

    Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.

    8.3B32K ctx Apache 2.0
    884Nov 2025gguf
    • Same category
    • Similar size (8.3B vs 8B)
    • Commercial use OK
    vs
  21. tiiuae logo≈5.3 GB

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

    7.6B256K ctx Falcon LLM License
    5KMay 2025gguf
    • Same category
    • Similar size (7.6B vs 8B)
    vs
  22. ByteDance-Seed logo

    academic-ds-9B

    ByteDance-Seed·Chat

    ≈7.5 GB

    This is a 9B model whose architecture is deepseek-v3, trained from scratch using 350B+ tokens from fully open-source, English-only datasets. It is designed for development and debugging purposes within the open-source community.

    9.4BA1.6B8K ctx Apache 2.0
    12.7KApr 2025gguf
    • Same category
    • Similar size (9.4B vs 8B)
    • Commercial use OK
    vs
  23. allenai logo≈6.3 GB

    Tülu3 is a leading instruction following model family, offering fully open-source data, code, and recipes designed to serve as a comprehensive guide for modern post-training techniques.

    8B128K ctx Llama 3.1 Community License
    9KNov 2024gguf
    • Same category
    • Similar size (8B vs 8B)
    vs
  24. ibm-granite logo

    granite-4.1-3b

    ibm-granite·Chat

    ≈3.1 GB

    Model Summary: Granite-4.1-3B is a 3B parameter long-context instruct model finetuned from Granite-4.1-3B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.

    3.4B128K ctx Apache 2.0
    436KApr 2026ollama
    • Same category
    • Smaller (3.4B vs 8B)
    • Commercial use OK
    vs