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 Cola2

120 open-weight models that do the same job as Cola2 (8.8B 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
ByteDance-Seed logo

Cola2

ByteDance-Seed·Chat

≈6.8 GB

Cola2 is a continuous-latent language model that co-adapts semantic compression and discrete text generation. It combines a dynamic-compression VAE, a block-causal Diffusion Transformer (DiT), and a span-causal token decoder with latent feedback.

8.8B32K ctx Unknown licence
1.2KNov 2026
--vram
any
--gpus
--quant
  1. NousResearch logo

    Hermes-3-Llama-3.1-8B

    NousResearch·Chat

    ≈6.3 GB

    Hermes 3 is the latest version of our flagship Hermes series of LLMs by Nous Research.

    8B128K ctx Llama 3 Community License
    336.5KJul 2024gguf
    • Same category
    • Similar size (8B vs 8.8B)
    vs
  2. tencent logo

    ContextPilot-8B

    tencent·Chat

    ≈6.5 GB

    ContextPilot-8B is the Qwen3-8B checkpoint of ContextPilot, a proactive context-management framework for long-horizon language-model agents. It teaches agents to plan, maintain long-term memory, and offload less useful context while they continue reasoning and using tools.

    8.2B40K ctx Custom licence
    877Aug 2026gguf
    • Same category
    • Similar size (8.2B vs 8.8B)
    vs
  3. google logo

    shieldgemma-9b

    google·Chat

    ≈8.6 GB

    ShieldGemma is a series of safety content moderation models built upon Gemma 2 that target four harm categories (sexually explicit, dangerous content, hate, and harassment).

    9.2B8K ctx Gemma Terms of Use
    256.9KJul 2024ollama
    • Same category
    • Similar size (9.2B vs 8.8B)
    vs
  4. internlm logo

    internlm3-8b-instruct

    internlm·Chat

    ≈6.1 GB

    InternLM3 has open-sourced an 8-billion parameter instruction model, InternLM3-8B-Instruct, designed for general-purpose usage and advanced reasoning. This model has the following characteristics:

    8.8B32K ctx Apache 2.0
    42.6KJan 2025gguf
    • Same category
    • Similar size (8.8B vs 8.8B)
    • Commercial use OK
    vs
  5. openbmb logo

    MiniCPM-SALA

    openbmb·Chat

    ≈6.4 GB

    MiniCPM-SALA (Sparse Attention and Linear Attention) is the first large-scale hybrid model effectively integrating sparse and linear attention for million-token context modeling

    9.5B512K ctx Apache 2.0
    4KFeb 2026
    • Same category
    • Similar size (9.5B vs 8.8B)
    • Commercial use OK
    vs
  6. Dream-org logo

    Dream-v0-Instruct-7B

    Dream-org·Chat

    ≈5.5 GB

    This is the instruct model of Dream 7B, which is an open diffusion large language model with top-tier performance. More details about the model and usage can be found in the blog and github bellow:

    7.6B128K ctx Apache 2.0
    71.9KApr 2025gguf
    • Same category
    • Similar size (7.6B vs 8.8B)
    • Commercial use OK
    vs
  7. ibm-granite logo

    granite-3.2-8b-instruct

    ibm-granite·Chat

    ≈6.6 GB

    Model Summary: Granite-3.2-8B-Instruct is an 8-billion-parameter, long-context AI model fine-tuned for thinking capabilities.

    8.2B128K ctx Apache 2.0
    51.3KFeb 2025ollama
    • Same category
    • Similar size (8.2B vs 8.8B)
    • Commercial use OK
    vs
  8. Unbabel logo

    Tower-Plus-9B

    Unbabel·Chat

    ≈8.6 GB

    Tower+ 9B is build on top of Gemma 2 9B. The model goes through the Continuous Pretraining (CPT), Instruction Tuning (IT), Weighted Preference Optimization (WPO). During all stages we include parallel and multilingual data (covering 22 languages).

    9.2B8K ctx CC BY-NC-SA 4.0
    18.5KJun 2025gguf
    • Same category
    • Similar size (9.2B vs 8.8B)
    vs
  9. 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
    130.8KAug 2026gguf
    • Same category
    • Similar size (4.7B vs 8.8B)
    • Commercial use OK
    vs
  10. empero-ai logo

    Qwythos-9B-v2

    empero-ai·Chat

    ≈7.2 GB

    The next iteration of Qwythos: all the reasoning of Qwythos-9B, with the looping behavior fixed. v2 keeps the deep chain-of-thought, the uncensored research posture, and the 1M-token context of its predecessor, and cleans up the rough edges that showed up in real use.

    9.7B1M ctx Apache 2.0
    1.3KJul 2026gguf
    • Same category
    • Similar size (9.7B vs 8.8B)
    • Commercial use OK
    vs
  11. 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
    • Smaller (4B vs 8.8B)
    • Commercial use OK
    • Widely used
    vs
  12. nvidia logo≈6.5 GB

    Orchestrator-8B is a state-of-the-art 8B parameter orchestration model designed to solve complex, multi-turn agentic tasks by coordinating a diverse set of expert models and tools.

    8.2B40K ctx Unknown licence
    4.2KNov 2025gguf
    • Same category
    • Similar size (8.2B vs 8.8B)
    vs
  13. swiss-ai logo

    Apertus-8B-2509

    swiss-ai·Chat

    ≈6.3 GB

    Apertus is a 70B and 8B parameter language model designed to push the boundaries of fully-open multilingual and transparent models.

    8.1B64K ctx Apache 2.0
    9.5KSept 2025gguf
    • Same category
    • Similar size (8.1B vs 8.8B)
    • Commercial use OK
    vs
  14. 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
    31KApr 2025gguf
    • Same category
    • Similar size (7.8B vs 8.8B)
    • Commercial use OK
    vs
  15. EssentialAI logo

    rnj-1-instruct

    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
    3.1KDec 2025ollama
    • Same category
    • Similar size (8.3B vs 8.8B)
    • Commercial use OK
    vs
  16. IlyaGusev logo

    saiga_llama3_8b

    IlyaGusev·Chat

    ≈6.3 GB

    I've changed the prompt format from ChatML to the original Llama-3 format in v4. Don't forget to switch formats!

    8B8K ctx Llama 3 Community License
    415.3KApr 2024gguf
    • Same category
    • Similar size (8B vs 8.8B)
    vs
  17. meta-llama logo

    Meta-Llama-3-8B-Instruct

    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
    419.8KApr 2024ollama
    • Same category
    • Similar size (8B vs 8.8B)
    vs
  18. 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
    82.6KJan 2025gguf
    • Same category
    • Similar size (7.6B vs 8.8B)
    • Commercial use OK
    vs
  19. allenai logo

    AstaBrief_8B

    allenai·Chat

    ≈6.4 GB

    AstaBrief-8B is a model trained to turn a research question and retrieved scientific literature excerpts into a cited report using only supervised fine-tuning and offline direct preference optimization.

    8B40K ctx Apache 2.0
    2.5KFeb 2026gguf
    • Same category
    • Similar size (8B vs 8.8B)
    • Commercial use OK
    vs
  20. 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
    3KDec 2025gguf
    • Same category
    • Similar size (8.2B vs 8.8B)
    • Commercial use OK
    vs
  21. 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
    22KApr 2025ollama
    • Same category
    • Similar size (9.4B vs 8.8B)
    • Commercial use OK
    vs
  22. 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
    26.7KSept 2025gguf
    • Same category
    • Similar size (6.9B vs 8.8B)
    • Commercial use OK
    vs
  23. 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
    961Sept 2026gguf
    • Same category
    • Similar size (7.4B vs 8.8B)
    • Commercial use OK
    vs
  24. ibm-granite logo≈7.5 GB

    Model Summary: Granite Switch 4.1 8B Preview is a modular LLM built on IBM Granite 4.1 8B with embedded adapters from the Granite Libraries collection.

    9.6B128K ctx Apache 2.0
    1.1KMay 2026
    • Same category
    • Similar size (9.6B vs 8.8B)
    • Commercial use OK
    vs