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 Hy4-flash

120 open-weight models that do the same job as Hy4-flash (220B 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
tencent logo

Hy4-flash

tencent·Vision

≈134 GB

Hy4 flash is our most cost-effective Hy model to date, featuring 220B total parameters (including 64B Engram parameters) with just 12B active parameters per token. It natively accepts text and image inputs, generates text, and supports a context window of up to 1M tokens.

220B1M ctx tencent-hy-license
5.6KNov 2026gguf
--vram
any
--gpus
--quant
  1. ByteDance-Seed logo

    UI-TARS-72B-SFT

    ByteDance-Seed·Vision

    ≈47 GB

    UI-TARS is a next-generation native GUI agent model designed to interact seamlessly with graphical user interfaces (GUIs) using human-like perception, reasoning, and action capabilities.

    73.4B32K ctx Apache 2.0
    252Jan 2025gguf
    • Same category
    • Smaller (73.4B vs 220B)
    • Commercial use OK
    vs
  2. OpenGVLab logo

    InternVL2_5-78B-MPO

    OpenGVLab·Vision

    ≈49 GB

    We introduce InternVL2.5-MPO, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. This series builds upon InternVL2.5 and Mixed Preference Optimization.

    78.4B32K ctx Qwen License
    124Dec 2024gguf
    • Same category
    • Smaller (78.4B vs 220B)
    vs
  3. Qwen logo

    Qwen3.5-4B-Base

    Qwen·Vision

    ≈4.3 GB

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

    4.7B256K ctx Apache 2.0
    496.7KFeb 2026gguf
    • Same category
    • Smaller (4.7B vs 220B)
    • Commercial use OK
    vs
  4. Zyphra logo

    ZAYA1-VL-8B

    Zyphra·Vision

    ≈6.6 GB

    ZAYA1-VL-8B is a vision-language model (VLM) built upon Zyphra's ZAYA1-8B LLM. It has state-of-the-art performance among VLMs for its size and inference efficiency.

    9.7B32K ctx Apache 2.0
    339.4KApr 2026gguf
    • Same category
    • Smaller (9.7B vs 220B)
    • Commercial use OK
    vs
  5. moonshotai logo

    Kimi-K3.1-Pro

    moonshotai·Vision

    ≈1701 GB

    Kimi K3.1 Pro is an open-weight, natively multimodal agentic model, and our most capable 3T-class model to date. Post-trained from Kimi K3 with large-scale joint reinforcement learning across hundreds of downstream domains, it is the first model in the K3.1 series.

    2.78T1M ctx kimi-k3.1-pro
    68KNov 2026gguf
    • Same category
    • Larger (2.78T vs 220B)
    vs
  6. Qwen logo≈2.6 GB

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

    2.1B256K ctx Apache 2.0
    1.2MOct 2025ollama
    • Same category
    • Smaller (2.1B vs 220B)
    • Commercial use OK
    vs
  7. google logo

    gemma-4-26B-A4B

    google·Vision

    ≈18 GB

    Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.

    26.5BA4B256K ctx Apache 2.0
    62.3KMar 2026gguf
    • Same category
    • Smaller (26.5B vs 220B)
    • Commercial use OK
    vs
  8. interfaze-ai logo

    interfaze-1-lite

    interfaze-ai·Vision

    ? GB

    Interfaze 1.1 Lite is a mixture-of-architectures (MoA) model for developer workloads: reading documents, transcribing speech, locating objects and interface elements, and answering over all of it with structured output.

    ?Binterfaze-open
    133Oct 2026
    • Same category
    vs
  9. meta-models logo

    Muse-Glimmer-30B-assistant

    meta-models·Vision

    ≈2.2 GB

    Muse Glimmer is a 30-billion-parameter causal language model with a dedicated perception encoder, distilled from Muse Spark and purpose-built for autonomous agentic tasks on consumer hardware.

    2.6B128K ctx Apache 2.0
    90.3KAug 2026
    • Same category
    • Smaller (2.6B vs 220B)
    • Commercial use OK
    vs
  10. Qwen logo

    Qwen3.5-2B-Base

    Qwen·Vision

    ≈2.2 GB

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

    2.3B256K ctx Apache 2.0
    321.5KFeb 2026gguf
    • Same category
    • Smaller (2.3B vs 220B)
    • Commercial use OK
    vs
  11. 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 220B)
    • Commercial use OK
    vs
  12. 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 220B)
    • Commercial use OK
    vs
  13. microsoft logo

    AesCode-32B

    microsoft·Vision

    ≈22 GB

    AesCode generates information-rich visual artifacts such as slides, posters, and dashboards as HTML/CSS. The output remains structured, editable, and verifiable, but the task poses a distinct challenge: code models cannot see how layout, hierarchy, and color come together on the canvas.

    33.4B256K ctx Apache 2.0
    1.3KSept 2026gguf
    • Same category
    • Smaller (33.4B vs 220B)
    • Commercial use OK
    vs
  14. 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 220B)
    • Commercial use OK
    vs
  15. openbmb logo

    MiniCPM-V-4.6

    openbmb·Vision

    ≈1.6 GB

    A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

    1.3B256K ctx Apache 2.0
    194.5KApr 2026ollama
    • Same category
    • Smaller (1.3B vs 220B)
    • Commercial use OK
    vs
  16. Qwen logo

    Qwen3.5-9B-Base

    Qwen·Vision

    ≈7.2 GB

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

    9.7B256K ctx Apache 2.0
    266.8KFeb 2026gguf
    • Same category
    • Smaller (9.7B vs 220B)
    • Commercial use OK
    vs
  17. nvidia logo

    Cosmos-Reason2-2B

    nvidia·Vision

    ≈2.5 GB

    NVIDIA Cosmos Reason 2 is an open, customizable, 2B-parameter reasoning vision language model (VLM) for physical AI and robotics that enables robots and vision AI agents to reason like humans, using prior knowledge, physics understanding and common sense to understand and act in the real world.

    2.4B256K ctx NVIDIA Open Model License
    475.6KDec 2025gguf
    • Same category
    • Smaller (2.4B vs 220B)
    • Commercial use OK
    vs
  18. 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 220B)
    • Commercial use OK
    vs
  19. Qwen logo≈5.8 GB

    In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models.

    8.3B125K ctx Apache 2.0
    5.2MJan 2025ollama
    • Same category
    • Smaller (8.3B vs 220B)
    • Commercial use OK
    • Widely used
    vs
    • Same category
    • Smaller (40B vs 220B)
    • Commercial use OK
    vs
  20. omlab logo

    VLX-Seek-1.5-10B

    omlab·Vision

    ≈7.4 GB

    VLX-Seek-1.5-10B is the open-source 10B model in the VLX-Seek 1.5 family, designed for fine-grained perception and visual grounding in embodied scenarios.

    10B256K ctx Apache 2.0
    73.4KJul 2026gguf
    • Same category
    • Smaller (10B vs 220B)
    • Commercial use OK
    vs
  21. tencent logo

    WeVisOne-VL-4B

    tencent·Vision

    ≈4.5 GB

    WeVisOne-VL (WeChat Vision All-in-One) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception…

    4.8B256K ctx Apache 2.0
    36.4KOct 2026gguf
    • Same category
    • Smaller (4.8B vs 220B)
    • Commercial use OK
    vs
  22. 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 220B)
    vs
  23. LiquidAI logo

    LFM2.5-VL-3B

    LiquidAI·Vision

    ≈2.8 GB

    LFM2.5-VL-3B is a multimodal variant of LFM2.5, a family of hybrid models designed for on-device deployment. It builds on LFM2-VL-3B with further mid- and post-training.

    3.1B32K ctx lfm1.0
    54.2KAug 2026gguf
    • Same category
    • Smaller (3.1B vs 220B)
    vs