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 MLExpert

120 open-weight models that do the same job as MLExpert (34.7B 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
InternScience logo

MLExpert

InternScience·Chat

≈22 GB

MLExpert is a 35B Mixture-of-Experts agentic model for autonomous machine learning engineering. It organizes experiments, writes and revises code, and improves solutions through sustained interaction with execution environments.

34.7BA3.5B256K ctx Apache 2.0
3.4KOct 2026gguf
--vram
any
--gpus
--quant
  1. InternScience logo

    Agents-A1

    InternScience·Chat

    ≈22 GB

    Agents‑A1 is a 35B Mixture‑of‑Experts agentic model from InternScience, built to scale heterogeneous agentic abilities across multiple domains including Long‑horizon Search, Engineering, Scientific Research, Instruction Following, and Tool-calling.

    35.1BA3.9B256K ctx Apache 2.0
    5KJun 2026gguf
    • Same category
    • Similar size (35.1B vs 34.7B)
    • Commercial use OK
    vs
  2. XingChen-AGI logo

    Xing4.0-29B-A4B

    XingChen-AGI·Chat

    ≈27 GB

    Xing4.0-29B-A4B is a next-generation large language model in the Xing series (formerly TeleChat), developed by China Telecom Artificial Intelligence Technology Co., Ltd. With 29B total parameters and only 4B activated per token, it natively supports a 256K context length, extensible to 512K.

    31.2BA4B256K ctx Apache 2.0
    5.4KSept 2026gguf
    • Same category
    • Similar size (31.2B vs 34.7B)
    • Commercial use OK
    vs
  3. Axion1-0 logo

    Axion-1.0-35B

    Axion1-0·Chat

    ≈22 GB

    This repository provides a reproduction checkpoint of Axion 1.0-35B, following the recipe described in Axion 1.0: Open Agent Foundation Models, Simplified. The model is designed for scientific reasoning, information seeking, and tool-augmented problem solving.

    35.1BA3.9B256K ctx Apache 2.0
    1.8KOct 2026gguf
    • Same category
    • Similar size (35.1B vs 34.7B)
    • Commercial use OK
    • Newer release
    vs
  4. Nanbeige logo

    Nanbeige4.3-33B-Base

    Nanbeige·Chat

    ≈22 GB

    In Nanbeige4.3, we take a foundational step toward pushing the boundaries of lightweight agents. Our strategy centers on building a high-capacity teacher agent first, which will subsequently anchor the distillation of advanced agentic capabilities into smaller models.

    33.1B128K ctx Apache 2.0
    2.2KOct 2026gguf
    • Same category
    • Similar size (33.1B vs 34.7B)
    • Commercial use OK
    • Newer release
    vs
  5. Looking for the post-trained model? See NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 for the full-precision release, or NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 for optimized inference.

    31.6BA3B256K ctx openmdw-1.1
    5.6KAug 2026gguf
    • Same category
    • Similar size (31.6B vs 34.7B)
    • Commercial use OK
    vs
  6. Qwen logo≈22 GB

    Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:

    32.8B32K ctx Apache 2.0
    718.6KSept 2024ollama
    • Same category
    • Similar size (32.8B vs 34.7B)
    • Commercial use OK
    vs
  7. ibm-granite logo

    granite-switch-4.1-30b

    ibm-granite·Chat

    ≈20 GB

    📝 Read the launch blog: Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint

    30B128K ctx Apache 2.0
    5KOct 2026gguf
    • Same category
    • Similar size (30B vs 34.7B)
    • Commercial use OK
    • Newer release
    vs
  8. ByteDance-Seed logo

    Seed-OSS-36B-Instruct

    ByteDance-Seed·Chat

    ≈24 GB

    Seed-OSS is a series of open-source large language models developed by ByteDance's Seed Team, designed for powerful long-context, reasoning, agent and general capabilities, and versatile developer-friendly features.

    36.2B512K ctx Apache 2.0
    43KAug 2025gguf
    • Same category
    • Similar size (36.2B vs 34.7B)
    • Commercial use OK
    vs
  9. LiquidAI logo

    LFM2.5-24B-A2B

    LiquidAI·Chat

    ≈15 GB

    LFM2.5-24B-A2B is a 24B-parameter reasoning model with only 2B active parameters, built for fast, private agents on-device. It is the largest and final model in the LFM2.5 family, which now spans two orders of magnitude: from LFM2.5-230M to LFM2.5-24B-A2B.

    24BA2B128K ctx lfm1.0
    31.6KOct 2026gguf
    • Same category
    • Similar size (24B vs 34.7B)
    • Newer release
    vs
  10. allenai logo≈22 GB

    We introduce Olmo 3, a new family of 7B and 32B models both Instruct and Think variants. Long chain-of-thought thinking improves reasoning tasks like math and coding.

    32.2B64K ctx Apache 2.0
    21.2KDec 2025ollama
    • Same category
    • Similar size (32.2B vs 34.7B)
    • Commercial use OK
    vs
  11. NousResearch logo

    Arete-27B

    NousResearch·Chat

    ≈19 GB

    We post-trained over Alibaba's Qwen3.8-27B to reinforce western values on a Chinese-trained model. We call this new model Arete-27B.

    27.4B256K ctx Apache 2.0
    7.5KNov 2026gguf
    • Same category
    • Similar size (27.4B vs 34.7B)
    • Commercial use OK
    • Newer release
    vs
  12. KRAFTON logo

    Raon-1-mini-preview

    KRAFTON·Chat

    ≈20 GB

    Raon-1 mini is a 30B-A4B Mixture-of-Experts (MoE) language model, designed and trained from scratch by KRAFTON AI. It demonstrates strong capabilities in Korean conversation and agentic tasks. As part of the Raon open model family, it is released under the Apache 2.0 license.

    28.8BApache 2.0
    4.9KOct 2026gguf
    • Same category
    • Similar size (28.8B vs 34.7B)
    • Commercial use OK
    • Newer release
    vs
  13. NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16 is a base large language model (LLM) trained from scratch by NVIDIA, with the next token prediction loss. It provides a good starting point for instruction fine-tuning.

    31.6BA3Bnvidia-nemotron-open-model-license
    18.9KDec 2025gguf
    • Same category
    • Similar size (31.6B vs 34.7B)
    • Commercial use OK
    vs
  14. ibm-granite logo

    granite-4.0-h-small

    ibm-granite·Chat

    ≈21 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.

    32.2BA8.8B128K ctx Apache 2.0
    25.6KSept 2025gguf
    • Same category
    • Similar size (32.2B vs 34.7B)
    • Commercial use OK
    vs
  15. allenai logo

    Olmo-3-1125-32B

    allenai·Chat

    ≈22 GB

    We introduce Olmo 3, a new family of 7B and 32B models. This suite includes Base, Instruct, and Think variants. The Base models were trained using a staged training approach.

    32.2B64K ctx Apache 2.0
    16.6KNov 2025ollama
    • Same category
    • Similar size (32.2B vs 34.7B)
    • Commercial use OK
    vs
  16. nvidia logo≈20 GB

    We're excited to introduce Nemotron-Cascade-2-30B-A3B, an open 30B MoE model with 3B activated parameters that delivers strong reasoning and agentic capabilities. It is post-trained from the Nemotron-3-Nano-30B-A3B-Base.

    31.6BA3B256K ctx NVIDIA Open Model License
    7KMar 2026ollama
    • Same category
    • Similar size (31.6B vs 34.7B)
    • Commercial use OK
    vs
  17. ibm-granite logo

    granite-4.1-30b

    ibm-granite·Chat

    ≈20 GB

    Model Summary: Granite-4.1-30B is a 30B parameter long-context instruct model finetuned from Granite-4.1-30B-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.

    28.9B128K ctx Apache 2.0
    11.9KApr 2026ollama
    • Same category
    • Similar size (28.9B vs 34.7B)
    • Commercial use OK
    vs
  18. llm-jp logo

    llm-jp-4-33b-base

    llm-jp·Chat

    ≈22 GB

    LLM-jp-4 is a series of large language models developed by the Research and Development Center for Large Language Models at the National Institute of Informatics.

    33.2B64K ctx Apache 2.0
    978Aug 2026
    • Same category
    • Similar size (33.2B vs 34.7B)
    • Commercial use OK
    vs
  19. ReadyArt logo≈27 GB

    scotoma‑1 writes very similarly to the base model. The J-Space projected refusal edit only lightly touched the prose.

    31.3B256K ctx Apache 2.0
    1.6KAug 2026gguf
    • Same category
    • Similar size (31.3B vs 34.7B)
    • Commercial use OK
    vs
  20. HemmingwayAI logo

    Hemmingway-1.5

    HemmingwayAI·Chat

    ≈18 GB

    The undetectable AI. Writing indistinguishable from a human's. 27B parameters, open weights, free for non-commercial use.

    26.9B256K ctx CC BY-NC 4.0
    3.6KOct 2026gguf
    • Same category
    • Similar size (26.9B vs 34.7B)
    • Newer release
    vs
  21. sarvamai logo

    sarvam-30b

    sarvamai·Chat

    ≈20 GB

    Sarvam-30B is an advanced Mixture-of-Experts (MoE) model with 2.4B non-embedding active parameters, designed primarily for practical deployment. It combines strong reasoning, reliable coding ability, and best-in-class conversational quality across Indian languages.

    32.2BA4.5B128K ctx Apache 2.0
    3.9KMar 2026gguf
    • Same category
    • Similar size (32.2B vs 34.7B)
    • Commercial use OK
    vs
  22. zai-org logo

    GLM-Z1-32B-0414

    zai-org·Chat

    ≈20 GB

    The GLM family welcomes a new generation of open-source models, the GLM-4-32B-0414 series, featuring 32 billion parameters. Its performance is comparable to OpenAI's GPT series and DeepSeek's V3/R1 series, and it supports very user-friendly local deployment features.

    32.6B32K ctx MIT
    37KApr 2025gguf
    • Same category
    • Similar size (32.6B vs 34.7B)
    • Commercial use OK
    vs
  23. Altworld logo

    Hemmingway-1

    Altworld·Chat

    ≈18 GB

    The AI that writes like a person. 27B parameters, open weights, free for non-commercial use.

    26.9B256K ctx CC BY-NC 4.0
    3.4KSept 2026gguf
    • Same category
    • Similar size (26.9B vs 34.7B)
    vs
  24. HemmingwayAI logo

    Hemmingway-1

    HemmingwayAI·Chat

    ≈18 GB

    The AI that writes like a person. 27B parameters, open weights, free for non-commercial use.

    26.9B256K ctx CC BY-NC 4.0
    3.4KSept 2026gguf
    • Same category
    • Similar size (26.9B vs 34.7B)
    vs