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 DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic

120 open-weight models that do the same job as DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic (9.4B 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

A compact 9B reasoning model distilled from DeepSeek-V4-Pro in Max Effect mode

9.4B256K ctx Apache 2.0
27KOct 2026gguf
--vram
any
--gpus
--quant
  1. XiaomiMiMo logo

    MiMo-7B-RL

    XiaomiMiMo·Chat

    ≈6.3 GB

    Currently, most successful RL works, including open-source research, rely on relatively large base models, e.g., 32B models, particularly for enhancing code reasoning capabilities.

    7.8B32K ctx MIT
    30.6KApr 2025gguf
    • Same category
    • Similar size (7.8B vs 9.4B)
    • Commercial use OK
    vs
  2. ibm-granite logo

    granite-4.0-h-tiny

    ibm-granite·Chat

    ≈5.2 GB

    📣 Update [10-07-2025]: Added a default system prompt to the chat template to guide the model towards more professional, accurate, and safe responses.

    6.9BA1.5B128K ctx Apache 2.0
    28.9KSept 2025gguf
    • Same category
    • Similar size (6.9B vs 9.4B)
    • Commercial use OK
    vs
  3. t-tech logo

    T-lite-it-2.1

    t-tech·Chat

    ≈6.5 GB

    T-lite-it-2.1 is an efficient Russian model built upon the Qwen 3 architecture, featuring significant improvements in instruction following and adds support for tool-calling capabilities — a key advancement over T-lite-it-1.0, which lacks tool-use support.

    8.2B40K ctx Apache 2.0
    3.1KDec 2025gguf
    • Same category
    • Similar size (8.2B vs 9.4B)
    • Commercial use OK
    vs
  4. speakleash logo

    Bielik-11B-v3.1-Instruct

    speakleash·Chat

    ≈8.3 GB

    Bielik-11B-v3.1-Instruct is a generative text model featuring 11 billion parameters. It is an update to the Bielik 11B v3 line that expands multilingual continual pre-training and strengthens post-training for instruction following, tool use, and reasoning.

    11.2B32K ctx Apache 2.0
    377Oct 2026gguf
    • Same category
    • Similar size (11.2B vs 9.4B)
    • Commercial use OK
    vs
  5. openbmb logo

    AgentCPM-Report

    openbmb·Chat

    ≈5.6 GB

    This repository contains AgentCPM-Report, an 8B-parameter deep research agent introduced in the paper AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research.

    8.2B64K ctx Apache 2.0
    2.2KJan 2026gguf
    • Same category
    • Similar size (8.2B vs 9.4B)
    • Commercial use OK
    vs
  6. openbmb logo

    MiniCPM4.1-8B

    openbmb·Chat

    ≈5.6 GB

    ✅ Strong Reasoning Capability: Surpasses similar-sized models on 15 tasks!

    8.2B64K ctx Apache 2.0
    6.2KSept 2025gguf
    • Same category
    • Similar size (8.2B vs 9.4B)
    • Commercial use OK
    vs
  7. zgcagi logo

    ZGCM-1-7B

    zgcagi·Chat

    ≈5.9 GB

    ZGCM-1 is a 7.39B-parameter dense language model trained from scratch, built for mathematical reasoning and tool-assisted search. It combines deliberate internal thinking with active information gathering, supporting 256K-token context and both thinking and direct-response modes in a single model.

    7.4B256K ctx MIT
    944Sept 2026gguf
    • Same category
    • Similar size (7.4B vs 9.4B)
    • Commercial use OK
    vs
  8. NousResearch logo

    Meta-Llama-3.1-8B-Instruct

    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
    135.6KJul 2024gguf
    • Same category
    • Similar size (8B vs 9.4B)
    vs
  9. nvidia logo≈9.8 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.

    13.5B256K ctx nvidia-nemotron-open-model-license
    6.5KApr 2026gguf
    • Same category
    • Similar size (13.5B vs 9.4B)
    • Commercial use OK
    vs
  10. nvidia logo≈6.8 GB

    NVIDIA-Nemotron-Nano-9B-v2-Base is a large language model (LLM) trained from scratch by NVIDIA that is designed as a completion model for a given piece of text. It uses a hybrid model architecture that consists primarily of Mamba-2 and MLP layers combined with just four Attention layers.

    8.9BNVIDIA Open Model License
    2.7KAug 2025gguf
    • Same category
    • Similar size (8.9B vs 9.4B)
    • Commercial use OK
    vs
  11. Qwen logo≈5.5 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 7B Qwen2 model.

    7.6B32K ctx Apache 2.0
    311.4KJun 2024ollama
    • Same category
    • Similar size (7.6B vs 9.4B)
    • Commercial use OK
    vs
  12. Qwen logo≈5.5 GB

    Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens. Compared to the Qwen2.5 128K version, Qwen2.5-1M demonstrates significantly improved performance in handling long-context tasks while maintaining its capability in short tasks.

    7.6B1M ctx Apache 2.0
    52.4KJan 2025gguf
    • Same category
    • Similar size (7.6B vs 9.4B)
    • Commercial use OK
    vs
  13. allenai logo≈8.7 GB

    We expand on our Olmo model series by introducing Olmo Hybrid, a new 7B hybrid RNN model in the Olmo family. Olmo Hybrid dramatically outperforms Olmo 3 in final performance, consistently showing roughly 2x data efficiency on core evals over the course of our pretraining run.

    7.4B32K ctx Apache 2.0
    3.1KFeb 2026
    • Same category
    • Similar size (7.4B vs 9.4B)
    • Commercial use OK
    vs
  14. Qwen logo

    Qwen2-7B

    Qwen·Chat

    ≈5.5 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 7B Qwen2 base language model.

    7.6B128K ctx Apache 2.0
    289.3KJun 2024gguf
    • Same category
    • Similar size (7.6B vs 9.4B)
    • Commercial use OK
    vs
  15. stepfun-ai logo

    PaCoRe-8B

    stepfun-ai·Chat

    ≈6.5 GB

    We introduce PaCoRe (Parallel Coordinated Reasoning), a framework that shifts the driver of inference from sequential depth to coordinated parallel breadth, breaking the model context limitation and massively scaling test time compute: Think in Parallel: PaCoRe launches massive parallel exploration…

    8.2B320K ctx MIT
    2.1KDec 2025gguf
    • Same category
    • Similar size (8.2B vs 9.4B)
    • Commercial use OK
    vs
  16. ibm-granite logo

    granite-3.1-8b-instruct

    ibm-granite·Chat

    ≈6.6 GB

    Model Summary: Granite-3.1-8B-Instruct is a 8B parameter long-context instruct model finetuned from Granite-3.1-8B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets tailored for solving long context problems.

    8.2B128K ctx Apache 2.0
    33.6KDec 2024gguf
    • Same category
    • Similar size (8.2B vs 9.4B)
    • Commercial use OK
    vs
  17. google logo≈4.6 GB

    T5Gemma is a family of lightweight yet powerful encoder-decoder research models from Google. These models are created by adapting pretrained decoder-only models into a encoder-decoder.

    5.6B8K ctx Gemma Terms of Use
    223.4KJun 2025
    • Same category
    • Similar size (5.6B vs 9.4B)
    vs
  18. openbmb logo

    MiniCPM4-8B

    openbmb·Chat

    ≈5.6 GB

    MiniCPM4 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.

    8.2B32K ctx Apache 2.0
    8.1KJun 2025gguf
    • Same category
    • Similar size (8.2B vs 9.4B)
    • Commercial use OK
    vs
  19. openbmb logo

    MiniCPM4-MCP

    openbmb·Chat

    ≈5.6 GB

    MiniCPM4 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.

    8.2B32K ctx Apache 2.0
    8.1KJun 2025gguf
    • Same category
    • Similar size (8.2B vs 9.4B)
    • Commercial use OK
    vs
  20. XiaomiMiMo logo

    MiMo-7B-Base

    XiaomiMiMo·Chat

    ≈6.3 GB

    Currently, most successful RL works, including open-source research, rely on relatively large base models, e.g., 32B models, particularly for enhancing code reasoning capabilities.

    7.8B32K ctx MIT
    15KApr 2025
    • Same category
    • Similar size (7.8B vs 9.4B)
    • Commercial use OK
    vs
  21. 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
    • Smaller (4B vs 9.4B)
    • Commercial use OK
    • Widely used
    vs
  22. utter-project logo

    EuroLLM-9B-Instruct

    utter-project·Chat

    ≈7.0 GB

    This is the model card for EuroLLM-9B-Instruct. You can also check the pre-trained version: EuroLLM-9B.

    9.2BApache 2.0
    11.1KNov 2024gguf
    • Same category
    • Similar size (9.2B vs 9.4B)
    • Commercial use OK
    vs
  23. IFM logo≈4.6 GB

    K2-Horizon-3.7B is the small dense member of the K2-Horizon family: a 3.7B-core decoder-only model with a 512K context window.

    5.1B512K ctx Apache 2.0
    15.2KSept 2026gguf
    • Same category
    • Similar size (5.1B vs 9.4B)
    • Commercial use OK
    vs
  24. mistralai logo≈5.8 GB

    The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.

    7.2B32K ctx Apache 2.0
    1.2MDec 2023ollama
    • Same category
    • Similar size (7.2B vs 9.4B)
    • Commercial use OK
    vs