Gemma 3n E4B IT
Model overview
gemma-3n-E4B-it
Google's current public Gemma 3n E4B multimodal on-device open-weight model.
general LLMreasoningvision-languageaudiospeechmultimodaledge / on-devicechatvoice assistantlocal inference
Representative version
gemma-3n-E4B-it
| Company | |
|---|---|
| Release | Not disclosed |
| Release type | Model release |
| Parameters | 8B / 4B active |
| Architecture | Not disclosed |
| Context | Not disclosed |
| Input modalities | text / image / audio |
| Output modalities | text |
| Tool use / function calling | Not disclosed |
| Structured output / reasoning | Not disclosed |
| Vision / audio / video | Confirmed: Vision, Audio; Not shown: Video |
| Open weights / License | Weights available / Gemma Terms of Use License sourcegoogle-gemma-3n-e4b-it-current · 2026-07-15 |
| Vendor API | Not disclosed API source pending verification |
| OpenRouter | OpenRouter listed |
| Pricing | OpenRouter · 2026-07-15: $0.06 / $0.12 input / output, per 1M tokens |
| Benchmark | No reliable public source |
| Public signals | 1 runtime / access record / 1 activity snapshot |
| Use cases | assistant chat / voice assistant / local inference / general text tasks |
| Claim evidence | Release / model specs / weightsgoogle/gemma-3n-E4B-it Hugging Face model cardgemma-3n-E4B-it |
OpenRouter
Pricing / context / availability
| OpenRouter | OpenRouter listed |
|---|---|
| OpenRouter listing | google/gemma-3n-e4b-it |
| Mapped version | gemma-3n-E4B-it google-gemma-3n-e4b-it-current |
| Pricing | OpenRouter · 2026-07-15: $0.06 / $0.12 input / output, per 1M tokens |
| Context | 32768 |
| Speed/Latency | No reliable public source |
| Snapshot time | 2026-07-15T20:11:41.551Z |
| Source | View source |
Public activity counters
Cumulative Hugging Face model-card downloads / likes / spaces
| Platform | Entry | Downloads | Likes | Spaces | Time | Source |
|---|---|---|---|---|---|---|
| huggingface | google/gemma-3n-E4B-it | 23,037 | 918 | 100 | 2026-07-15T20:11:41.551Z | View source |
Operations
Runtime / access signals
| Time | Signal | Original text | Source |
|---|---|---|---|
| 12/21/2025, 06:05 PM UTC | Broken audio handling | Audio handling seems to break for pretty much all use-cases that don't exclusively involve transcription, summarization or translation. For... | Source |
Evidence gaps
Public display boundary
Release date not disclosedNo reliable benchmark sourceNo linkable real reviewSpeed/latency not disclosed