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 Darwin-180B-RSI-R3

120 open-weight models that do the same job as Darwin-180B-RSI-R3 (180B vision), 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
FINAL-Bench logo

Darwin-180B-RSI-R3

FINAL-Bench·Vision

≈108 GB

💻 Run it on your own machine: POCKET-Darwin-180B-GGUF, the 4-bit GGUF of R3 (111 GB), runs on a laptop with an 8 GB GPU and 32 GB RAM, CPU only at 18–21 tok/s, a 128 GB mini PC or one DGX Spark. MMLU-Pro is identical to BF16 (87.65%).

180BA61.6B256K ctx qwen-community-1.0
1.1KOct 2026gguf
--vram
any
--gpus
--quant
  1. thinkingmachines logo

    Inkling-2-Mini

    thinkingmachines·Vision

    ≈17 GB

    Inkling 2 Mini is a general-purpose multimodal model that accepts text and image inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages.

    26.4BA3.5B1M ctx Apache 2.0
    7.9KNov 2026ollama
    • Same category
    • Smaller (26.4B vs 180B)
    • Commercial use OK
    • Newer release
    vs
  2. internlm logo

    Intern-S2-Mobius

    internlm·Vision

    ≈22 GB

    We introduce Intern-S2-Mobius, a 35B foundation model built on the Mobius-v0 architecture realized by Xtuner and LMDeploy.

    36B256K ctx Apache 2.0
    1KJul 2026
    • Same category
    • Smaller (36B vs 180B)
    • Commercial use OK
    vs
  3. internlm logo

    Intern-S2-Preview

    internlm·Vision

    ≈23 GB

    We introduce Intern-S2-Preview, an efficient 35B scientific multimodal foundation model. Beyond conventional parameter and data scaling, Intern-S2-Preview explores task scaling: increasing the difficulty, diversity, and coverage of scientific tasks to further unlock model capabilities.

    36.1BA4.9B256K ctx Apache 2.0
    1.6KMay 2026
    • Same category
    • Smaller (36.1B vs 180B)
    • Commercial use OK
    vs
  4. moonshotai logo

    Kimi-K3

    moonshotai·Vision

    ≈1701 GB

    Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window.

    2.78T1M ctx kimi-k3
    731KJun 2026ollama
    • Same category
    • Larger (2.78T vs 180B)
    vs
  5. nvidia logo≈1.4 GB

    NVIDIA Nemotron Parse 2.0 transforms document images into structured, machine-readable representations with text, layout classes, bounding boxes, and reading-order information.

    903M9K ctx Custom licence
    650.6KJun 2026
    • Same category
    • Smaller (903M vs 180B)
    • Commercial use OK
    vs
  6. orcarouter logo

    Qwen3.8-27B-Uncensored

    orcarouter·Vision

    ≈19 GB

    One Gateway. Every Model. — Route Smarter · Ship Safer · Spend Less.

    27.8BApache 2.0
    8KAug 2026gguf
    • Same category
    • Smaller (27.8B vs 180B)
    • Commercial use OK
    vs
    • Same category
    • Smaller (40B vs 180B)
    • Commercial use OK
    vs
  7. nvidia logo

    Flora-Rewarder

    nvidia·Vision

    ≈19 GB

    Flora-rewarder-27B produces outcome rewards (an episode-level success score), used for monitoring real-world deployments, and process rewards (dense action-quality scores over short time steps), used during reinforcement learning-based post-training.

    27.8B256K ctx NVIDIA Non-Commercial License
    4.9KOct 2026
    • Same category
    • Smaller (27.8B vs 180B)
    • Newer release
    vs
  8. naver-hyperclovax logo

    HyperCLOVAX-SEED-Think-32B

    naver-hyperclovax·Vision

    ≈23 GB

    HyperCLOVA X SEED 32B Think is an updated vision-language thinking model that advances the SEED Think 14B line beyond simple scaling, pairing a unified vision-language Transformer backbone with a reasoning-centric training recipe.

    33.3B128K ctx hyperclovax
    7.5KDec 2025gguf
    • Same category
    • Smaller (33.3B vs 180B)
    vs
  9. nvidia logo≈22 GB

    NVIDIA-Ising-Calibration-1 analyzes quantum computing calibration experiment plots and generates structured technical text across six analysis question categories. NVIDIA-Ising-Calibration-1 was developed by NVIDIA as a quantum calibration vision-language model built on Qwen3.5-35B-A3B.

    35BA3B256K ctx NVIDIA Open Model License
    2KMar 2026gguf
    • Same category
    • Smaller (35B vs 180B)
    • Commercial use OK
    vs
  10. nvidia logo

    Flora-Captioner

    nvidia·Vision

    ≈19 GB

    Flora-captioner-27B generates one action instruction for a supplied target interval in a robot or human manipulation video. It uses neighboring video context to disambiguate the intended local operation.

    27.4B256K ctx NVIDIA Non-Commercial License
    4.7KOct 2026
    • Same category
    • Smaller (27.4B vs 180B)
    vs
  11. OpenGVLab logo

    InternVL3_5-38B

    OpenGVLab·Vision

    ≈25 GB

    We introduce InternVL3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL series.

    38.4B40K ctx Apache 2.0
    4.3KAug 2025gguf
    • Same category
    • Smaller (38.4B vs 180B)
    • Commercial use OK
    vs
  12. tencent logo

    WeMM-Video-35BA3B

    tencent·Vision

    ≈23 GB

    WeMM-Video-35B-A3B is the mixture-of-experts (35B total, 3B active) checkpoint in the WeMM-Video family. WeMM-Video is a Chinese–English bilingual family for joint audio-visual understanding and reasoning. It accepts text, images, audio, and video and generates text responses.

    36.2BA5B256K ctx Apache 2.0
    239Nov 2026gguf
    • Same category
    • Smaller (36.2B vs 180B)
    • Commercial use OK
    • Newer release
    vs
  13. BAAI logo

    AREX-2

    BAAI·Vision

    ≈19 GB

    AREX-2 is a 27B-parameter long-horizon agent model from the Beijing Academy of Artificial Intelligence (BAAI). It learns to improve a solution over multiple test-time rounds: propose, measure, reflect, and revise.

    27.4B256K ctx Apache 2.0
    3.9KSept 2026gguf
    • Same category
    • Smaller (27.4B vs 180B)
    • Commercial use OK
    vs
  14. 🔥 Update (April 5): I’ve released the complete training notebook, codebase, and a comprehensive PDF guide to help beginners and enthusiasts understand and reproduce this model's fine-tuning process.

    27.8B256K ctx Apache 2.0
    18.6KFeb 2026gguf
    • Same category
    • Smaller (27.8B vs 180B)
    • Commercial use OK
    vs
  15. Qwen logo≈4.3 GB

    Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.

    4.4B256K ctx Apache 2.0
    2.8MOct 2025ollama
    • Same category
    • Smaller (4.4B vs 180B)
    • Commercial use OK
    • Widely used
    vs
  16. Qwen logo

    Qwen3.5-0.8B-Base

    Qwen·Vision

    ≈1.4 GB

    Over recent months, we have intensified our focus on developing foundation models that deliver exceptional utility and performance.

    873M256K ctx Apache 2.0
    880.7KFeb 2026gguf
    • Same category
    • Smaller (873M vs 180B)
    • Commercial use OK
    vs
  17. meta-llama logo

    Llama-3.2-90B-Vision

    meta-llama·Vision

    ≈56 GB

    The Llama 3.2-Vision collection of multimodal large language models (LLMs) is a collection of pretrained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text \+ images in / text out).

    88.6B128K ctx Llama 3.2 Community License
    21Sept 2024
    • Same category
    • Smaller (88.6B vs 180B)
    vs
  18. google logo

    gemma-3-27b-it

    google·Vision

    ≈21 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.

    27.4B128K ctx Gemma Terms of Use
    271.1KMar 2025ollama
    • Same category
    • Smaller (27.4B vs 180B)
    vs
  19. fastino logo

    GLiDE

    fastino·Vision

    ≈18 GB

    GLiDE is a decision model from Fastino. Given a state (text or JSON, optionally with images) and one or more typed questions, it returns a probability for every option of every question. Internal use only.

    26.1B256K ctx fastino-community
    3.7KOct 2026
    • Same category
    • Smaller (26.1B vs 180B)
    • Newer release
    vs
  20. fastino logo

    GLiDE-27B

    fastino·Vision

    ≈18 GB

    Inference provider: Fastino — use GLiDE through Fastino's hosted API (POST https://api.fastino.ai/v1/systemone, model fastino/GLiDE). Get an API key · API documentation

    26.1B256K ctx fastino-community
    3.7KOct 2026gguf
    • Same category
    • Smaller (26.1B vs 180B)
    • Newer release
    vs
  21. microsoft logo

    Fara1.5-27B

    microsoft·Vision

    ≈19 GB

    Fara1.5-27B is a multimodal computer use agent (CUA) for web browsers, from Microsoft Research AI Frontiers. It observes the browser through screenshots and acts on the user's behalf by emitting structured tool calls — click, type, scroll, visit URL, web search, and so on — to complete tasks…

    27.4B256K ctx MIT
    4.3KJul 2026gguf
    • Same category
    • Smaller (27.4B vs 180B)
    • Commercial use OK
    vs
  22. Agnes-AI logo

    Agnes-3.0-Flash

    Agnes-AI·Vision

    ≈22 GB

    This repository contains an earlier open-weight Preview checkpoint of Agnes 3.0 Flash. It is distinct from the newer production/API checkpoint listed on Artificial Analysis. The Preview release has 33B parameters and a context window of 262,144 tokens.

    33.1B256K ctx Apache 2.0
    447Sept 2026gguf
    • Same category
    • Smaller (33.1B vs 180B)
    • Commercial use OK
    vs
  23. Skywork logo

    Skywork-R1V-38B

    Skywork·Vision

    ≈25 GB

    Skywork-R1V-38B is an open-weight vision model with 38.4B parameters from Skywork, published on Hugging Face.

    38.4B128K ctx MIT
    7.8KMar 2025
    • Same category
    • Smaller (38.4B vs 180B)
    • Commercial use OK
    vs