edge LLM
Gemma 4 E4B
Google's small Gemma 4 model for CPU and edge use.
Levelmodel
Classedge LLM
Parameters8B
Context128,000
Released2 Apr 2026
Opennessopen weights permissive
Runs onlaptop, mobile or NPU, offline capable
Statusactive
Benchmark Results
maintainer-run
SEA-HELMSoutheast Asian and Indonesian
Checkpoint gemma-4-E4B-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstrapsmaintainer-run
69.65 95% CI [-1.40, +1.30]
04080
Score in score. Higher is better.
SEA-HELM leaderboard, 58 models, Indonesian (ID)
Checkpoint gemma-4-E4B-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstrapsmaintainer-run
66.3 95% CI [-0.65, +0.65]
04080
Score in score. Higher is better.
SEA-HELM leaderboard, 58 models, SEA average
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Identity
- Developer
- Google, Google DeepMind
- Family
- Gemma 4
- Released
- 2 Apr 2026 sourcesannouncement page
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer Dense with Per-Layer Embeddings
- Total parameters
- 8B sources
- Active parameters
- 4.5B
- Checkpoint parameters
- –
- Note
- 4.5B effective (8B with embeddings)
- Context length
- 128,000 tokens
- Input
- text, image, audio
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- Apache License 2.0 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- laptop, mobile or NPU, offline capable
- Footprint
- About 2.5 GB at Q4_K_M; 2 to 3 GB at 4-bit. Phones with 6 GB+ RAM, iPhone 14 Pro+, Apple Silicon. Snapdragon 8 Gen 3: 12 to 20 tok/s (third-party estimate)
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelGemma 4 E4BGoogle, edge LLM
Gemma 4 E4BGoogle, edge LLMUse CasesIndustrial Copilots and Maintenance AssistantsIndustrialIndonesian and Regional-Language LLMsPublic SectorTelecom Domain LLMs and BenchmarksTelecomUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026
Siemens Erlangen electronics factoryPlanned, 6 Jan 2026
ADNOC OffshoreIn production, 9 Sep 2025
Aker BPIn production, 9 Sep 2025+10 moreDeployments of these use cases; none names this model.
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026Siemens Erlangen electronics factoryPlanned, 6 Jan 2026ADNOC OffshoreIn production, 9 Sep 2025Aker BPIn production, 9 Sep 2025+10 moreDeployments of these use cases; none names this model.Sources
- google/gemma-4-31B-it , Hugging Face huggingface.co https://huggingface.co/google/gemma-4-31B-it
- google (Google) huggingface.co https://huggingface.co/google
- जेम्मा रिलीज़ | Gemma | Google AI for Developers ai.google.dev https://ai.google.dev/gemma/docs/releases
- Google Releases Gemma 4: Open Models Under Apache 2.0 datanorth.ai https://datanorth.ai/news/google-releases-gemma-4-open-models
- Gemma 4 E2B vs E4B: How to Run a Multimodal AI Model on Your Phone mindstudio.ai https://www.mindstudio.ai/blog/gemma-4-e2b-e4b-edge-models-phone-local
- Gemma 4: Byte for byte, the most capable open models blog.google https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Gemma 4 E4B", https://aurion.semai.id/models/google-gemma-4-e4b/, records of October 2026.