Gemma 4 26B A4B IT
Google · open weights · served by 36 providers · reasoning
google/gemma-4-26b-a4b-it
- Weights
- Open
- Released
- 2026-04-02
- Knowledge cutoff
- 2025-04
- Context window
- 262K
google/gemma-4-26B-A4B-it at commit 4d7ae4984b, last changed 2026-07-20
- Licence
- apache-2.0
- Access
- Open download
- Library
- transformers
- Formats
- .safetensors
- No model signature file is published with the weights.
- Built on google/gemma-4-26B-A4B.
What the Hub's scanners report
2 weight files, 2 with a scan result. No scanner reports an issue with them.
Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.
- Adaptiongemma-4-26b-a4b-it
- AIHubMixgemma-4-26b-a4b-it-free
- AI/ML APIgoogle/gemma-4-26b-a4b-it
- AKI.IOgemma4-26b
- Amazon Bedrockgoogle.gemma-4-26b-a4b
- Cloudflare Workers AI@cf/google/gemma-4-26b-a4b-it
- Cortecsgemma-4-26b-a4b-it
- Deep Infragoogle/gemma-4-26B-A4B-it
- EmpirioLabs AIgemma-4-26b-a4b
- evrocgoogle/gemma-4-26B-A4B-it
- Frequencygoogle/gemma-4-26b-a4b-it
- Vertexgoogle/gemma-4-26b-a4b-it-maasalpha
- GreenPTgemma4
- Hugging Facegoogle/gemma-4-26B-A4B-it
- Charm Hypergemma-4-26b-a4b-it
- Kilo Gatewaygoogle/gemma-4-26b-a4b-it
- DevPass (LLM Gateway)gemma-4-26b-a4b-it
- LLM Gatewaydeepinfra/gemma-4-26b-a4b-it
- LLM Gatewayflexai/gemma-4-26b-a4b-it
- LLM Gatewaynovita/gemma-4-26b-a4b-it
- Merge Gatewaygoogle/gemma-4-26b-a4b-it
- NaNgemma4
- NanoGPTgoogle/gemma-4-26b-a4b-it
- NanoGPTgoogle/gemma-4-26b-a4b-it:thinking
12 more providers
Novita AI (google/gemma-4-26b-a4b-it), OpenRouter (google/gemma-4-26b-a4b-it), OpenRouter (google/gemma-4-26b-a4b-it:free), OrcaRouter (google/gemma-4-26b-a4b-it), Powerspring (gemma-4-26b-a4b), Requesty (gemma-4-26b-a4b-it), Scaleway (gemma-4-26b-a4b-it), SiliconFlow (google/gemma-4-26B-A4B-it), TrustedTokens (google/gemma-4-26B-A4B-it), Venice AI (google-gemma-4-26b-a4b-it), Vercel AI Gateway (google/gemma-4-26b-a4b-it), CoreWeave (google/gemma-4-26B-A4B-it)
Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.
- vllm · 131 advisories
- transformers · 24 advisories
- keras · 20 advisories
- onnx · 17 advisories
- bentoml · 16 advisories
- github.com/ollama/ollama · 16 advisories
- torch · 13 advisories
- lmdeploy · 10 advisories
- sglang · 10 advisories
- skops · 4 advisories
Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.