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 h2o-lightning-31b

120 open-weight models that do the same job as h2o-lightning-31b (31.3B 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
h2oai logo

h2o-lightning-31b

h2oai·Vision

≈21 GB

H2O-Lightning-31B is a 31B-parameter decision model from H2O.ai, built on google/gemma-4-31B-it. It answers typed decision questions about a record (a document, a ticket, a policy, a conversation), and about images that come with the record. It returns a probability for every option:

31.3Bh2o-model-non-commercial-licence-v1.1
690Oct 2026
--vram
any
--gpus
--quant
  1. 🔥 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
    14.2KFeb 2026gguf
    • Same category
    • Similar size (27.8B vs 31.3B)
    • Commercial use OK
    vs
  2. 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
    1.4KSept 2026gguf
    • Same category
    • Similar size (33.4B vs 31.3B)
    • Commercial use OK
    vs
  3. 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
    3.6KOct 2026
    • Same category
    • Similar size (26.1B vs 31.3B)
    vs
  4. 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
    3.6KOct 2026gguf
    • Same category
    • Similar size (26.1B vs 31.3B)
    vs
  5. 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
    4.2KJul 2026gguf
    • Same category
    • Similar size (27.4B vs 31.3B)
    • Commercial use OK
    vs
  6. inclusionAI logo

    LBS-27B

    inclusionAI·Vision

    ≈19 GB

    LBS-27B is an agentic vision-language model based on Qwen3.8-27b. It learns to select and inspect image regions through GUI grounding, then transfers this observation policy to general-domain visual question answering and high-resolution perception.

    27B256K ctx Apache 2.0
    1.9KOct 2026gguf
    • Same category
    • Similar size (27B vs 31.3B)
    • Commercial use OK
    • Newer release
    vs
  7. sensenova logo

    SenseNova-6.8-Code2Video

    sensenova·Vision

    ≈19 GB

    We present SenseNova 6.8 Code2Video, a lightweight open model for code-driven video creation. The model builds and renders videos by generating executable code, and currently focuses on short videos implemented entirely in code.

    27.4B256K ctx Apache 2.0
    1.7KOct 2026gguf
    • Same category
    • Similar size (27.4B vs 31.3B)
    • Commercial use OK
    • Newer release
    vs
  8. google logo

    medgemma-27b-it

    google·Vision

    ≈21 GB

    This section describes the MedGemma model and how to use it.

    28.8B128K ctx health-ai-developer-foundations
    36.4KJul 2025ollama
    • Same category
    • Similar size (28.8B vs 31.3B)
    vs
  9. FreedomIntelligence logo

    HuatuoGPT-3-27B

    FreedomIntelligence·Vision

    ≈19 GB

    HuatuoGPT-3-27B is a medical LLM built on Qwen3.8-27B with One-stage Policy Optimization (OnePO). OnePO adapts language models to medicine in a single reinforcement-learning stage, without preceding domain-specific supervised fine-tuning.

    27B256K ctx Apache 2.0
    2.3KSept 2026gguf
    • Same category
    • Similar size (27B vs 31.3B)
    • Commercial use OK
    vs
  10. inclusionAI logo

    ZwZ2-27B

    inclusionAI·Vision

    ≈19 GB

    ZwZ2-27B is the Qwen3.6-27B-based model in Zooming-without-Zooming-v2 (ZwZ2). It learns to connect visual evidence across regions through comparison, aggregation, matching, and multi-step reasoning. Training uses full images; inference requires no zooming tools.

    27.4B256K ctx Unknown licence
    1.5KOct 2026gguf
    • Same category
    • Similar size (27.4B vs 31.3B)
    vs
  11. 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
    7KDec 2025gguf
    • Same category
    • Similar size (33.3B vs 31.3B)
    vs
  12. Qwen logo≈20 GB

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

    31.1BA3B256K ctx Apache 2.0
    7.2KSept 2025gguf
    • Same category
    • Similar size (31.1B vs 31.3B)
    • Commercial use OK
    vs
  13. OpenGVLab logo

    InternVL3_5-30B-A3B

    OpenGVLab·Vision

    ≈20 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.

    30.8BA3B40K ctx Apache 2.0
    7.7KAug 2025gguf
    • Same category
    • Similar size (30.8B vs 31.3B)
    • Commercial use OK
    vs
    • Same category
    • Similar size (27.8B vs 31.3B)
    • Commercial use OK
    vs
  14. google logo

    translategemma-27b-it

    google·Vision

    ≈21 GB

    TranslateGemma is a family of lightweight, state-of-the-art open translation models from Google, based on the Gemma 3 family of models. TranslateGemma models are designed to handle translation tasks across 55 languages.

    28.8B128K ctx Gemma Terms of Use
    4.3KJan 2026ollama
    • Same category
    • Similar size (28.8B vs 31.3B)
    vs
  15. 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
    485Sept 2026gguf
    • Same category
    • Similar size (33.1B vs 31.3B)
    • Commercial use OK
    vs
  16. tencent logo

    Hy-Embodied-VLM-1.0

    tencent·Vision

    ≈19 GB

    Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world.

    30.5B32K ctx Apache 2.0
    579Jul 2026
    • Same category
    • Similar size (30.5B vs 31.3B)
    • Commercial use OK
    vs
  17. trohrbaugh logo

    Qwen3.8-27B-heretic-ara

    trohrbaugh·Vision

    ≈19 GB

    Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.

    27.4B256K ctx Apache 2.0
    1.2KAug 2026gguf
    • Same category
    • Similar size (27.4B vs 31.3B)
    • Commercial use OK
    vs
  18. baidu logo≈18 GB

    The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations:

    29.4BA3B128K ctx Apache 2.0
    12KJun 2025
    • Same category
    • Similar size (29.4B vs 31.3B)
    • Commercial use OK
    vs
  19. philbert440 logo

    Qwen3.8-27B-Uncensored-Cyber

    philbert440·Vision

    ≈19 GB

    Cyber-specialized de-refusal of Qwen3.8-27B: fully open on the cyber/offensive-security domain while keeping reasoning, factual accuracy, and coherence intact. Vision tower and MTP speculative-decoding head are preserved (full multimodal, image-text-to-text).

    27.4B256K ctx Apache 2.0
    931Aug 2026gguf
    • Same category
    • Similar size (27.4B vs 31.3B)
    • Commercial use OK
    vs
  20. 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
    1.1KJul 2026
    • Same category
    • Similar size (36B vs 31.3B)
    • Commercial use OK
    vs
  21. 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
    1.7KMay 2026
    • Same category
    • Similar size (36.1B vs 31.3B)
    • Commercial use OK
    vs
  22. 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
    1.9KMar 2026gguf
    • Same category
    • Similar size (35B vs 31.3B)
    • Commercial use OK
    vs
  23. IMPORTANT: NEO and NEO MAX MTP GGUFS, along with complete model card detailing all the reasoning and instruct modes are here:

    27.8B256K ctx Apache 2.0
    574Aug 2026gguf
    • Same category
    • Similar size (27.8B vs 31.3B)
    • Commercial use OK
    vs