LIVE
Study measures how coding agents pick third-party tools03/09/26|OpenAI's GPT-6 Astra sets new state-of-the-art on ARC-AGI-303/09/26 · OpenAI|ESPO: A Prompt Optimization Method That Beats GEPA With Shorter, More Stable Prompts03/09/26|"Last Translation Benchmark": a large-scale collaborative effort for a definitive MT benchmark03/09/26|NVIDIA pushes local AI at IFA 2026 with RTX Spark PCs and a personal inference router03/09/26 · NVIDIA|Google DeepMind unveils WeatherNext 3, its most accurate weather AI model yet03/09/26 · Google DeepMind|OpenAI Launches $1B Daybreak Program for Frontline Cybersecurity Defenders03/09/26 · OpenAI|Hcompany releases NeoMME, a compact multimodal-native encoder for retrieval03/09/26 · Hcompany|Playco cuts manual fixes by 50% using GPT-6 Astra for prototyping03/09/26 · OpenAI|Legora reviews 41 financial documents in minutes with GPT-6 Astra03/09/26 · OpenAI|Hugging Face open-sources a project training a coding model to paint watercolours03/09/26 · Hugging Face|A 350M-Parameter Model Improved in 100 GRPO Steps for Better Structured Outputs03/09/26|Study measures how coding agents pick third-party tools03/09/26|OpenAI's GPT-6 Astra sets new state-of-the-art on ARC-AGI-303/09/26 · OpenAI|ESPO: A Prompt Optimization Method That Beats GEPA With Shorter, More Stable Prompts03/09/26|"Last Translation Benchmark": a large-scale collaborative effort for a definitive MT benchmark03/09/26|NVIDIA pushes local AI at IFA 2026 with RTX Spark PCs and a personal inference router03/09/26 · NVIDIA|Google DeepMind unveils WeatherNext 3, its most accurate weather AI model yet03/09/26 · Google DeepMind|OpenAI Launches $1B Daybreak Program for Frontline Cybersecurity Defenders03/09/26 · OpenAI|Hcompany releases NeoMME, a compact multimodal-native encoder for retrieval03/09/26 · Hcompany|Playco cuts manual fixes by 50% using GPT-6 Astra for prototyping03/09/26 · OpenAI|Legora reviews 41 financial documents in minutes with GPT-6 Astra03/09/26 · OpenAI|Hugging Face open-sources a project training a coding model to paint watercolours03/09/26 · Hugging Face|A 350M-Parameter Model Improved in 100 GRPO Steps for Better Structured Outputs03/09/26|
🇺🇸 United States generalistReleased March 2026

Gemma 4 26B-A4B

Google
Open-sourceSelf-hostRGPD
Verdict

A solid pick for self-hosting and full data control.

Skill profile

Arena Elo1438

Not disclosed

Strengths

  • World-class on Arena
  • Open-source and self-hostable

Limitations

  • API pricing not disclosed

Who is it for

A good fit if…
  • you want to control cost or self-host
  • you have GDPR constraints
Skip it if…

    Access & availability

    Self-hostable (open weights)

    Key specifications

    Context
    256K
    Input price
    Output price
    Speed
    Price not auditedBenchmarks not audited

    Privacy

    GDPR-compliant

    Run it locally

    Desktop with solid GPU / 32GB+ Mac8.2M1k
    QuantizationDiskRAM / VRAMTypical hardware
    Q4 · recommended14.8 GB18 GB32GB PC / 24GB Mac / RTX 4070 Ti+
    Q8 · balanced27.8 GB33 GB64GB Mac / dual 24GB GPUs
    FP16 · max quality52 GB59 GB96-128GB Mac Studio / 4× GPUs

    Estimates for a moderate context. Long contexts need more RAM (KV cache).

    Advanced data · for experts
    Architecture, modalities, detailed cost, full benchmarks
    Architecture
    Size
    26B (MoE, 4B actifs)
    Cutoff date
    Inputs
    text
    Outputs
    text
    License
    apache-2.0
    Hosting
    Hallucination score
    Estimated cost (API)
    Typical exchange (~3k in / 1k out)
    Not disclosed
    1M in + 1M out
    Not disclosed
    All benchmarks
    Arena Elo1438
    MMLU
    GPQA
    HumanEval
    SWE-Bench
    MATH

    Similar models