Gemma 4 E2B (Unsloth)
Gemma 4 E2B is the most compact Gemma 4 model and the entry point into the new family under the Apache 2.0 license. PLE architecture with 5.1B total and 2.3B effective parameters, 128,000 tokens of context, multimodal input for text, image, and audio, plus built-in reasoning and function calling. Runs locally as Unsloth GGUF on Edge- and phone-class hardware.
- Open Weights
- Edge
- llama.cpp
- Text
- Vision
- Audio
- Instruction-Tuned
- Real-Time
Sovereign Risk: LOW Google DeepMind releases Gemma 4 under Apache 2.0 with open weights, and the Unsloth GGUF build supports fully local inference. Since the model can be run offline, the operational data exfiltration risk is low.
Key metrics
Score · Latency · Cost · Quality
- Total Score Silver
- 68.13
- Routine
- 40.79
- Reasoning
- 27.34
- LLM Judge Avg
- 3.49 / 5
- 100 Coverage
- Avg Task Duration
- 10.41s
- Real-Time
- Token Rate
- 67.09tok/s
- Output Rate
- P95 Latency
- 23.82s
- Top 5 %
- Total Tokens
- 66000
- Output Volume
- Cost per 1K
- $0
- USD / 1K Requests
- Benchmark Cost
- $0
- Total · 66000 tok
Benchmark modules
10 modules · weighted · vs. model median & top performer
Gemma 4 E2B (Unsloth)
Best model
Ø All models
Code Quality
71.4
CLI Benchmark
85.56
Logical Reasoning
69.4
UX Writing
63.45
Documentation
58.26
Content Transform.
74.15
Cultural Intelligence
72.3
Synthesis Quality
50
Tool Execution
68.33
ToolUse Score
59.25
Benchmark Cost
$0
Token efficiency & latency
Consumption per module vs. model median
Token consumption per module
Performance profile
Key metrics – legend
Score
- Total Score
- Overall score derived from Routine and Reasoning scores. Basis for the fleet rank and tier assignment (Gold / Silver / Bronze / Standard).
- Routine
- Score for standard tasks: code generation, text transformation, structured outputs. Weighted by task complexity.
- Reasoning
- Score for analytical and logical tasks: multi-step problem solving, mathematical reasoning, structured argumentation.
- Rank
- Position in the fleet comparison, sorted by Total Score. Refers to the snapshot at the time of testing.
LLM Judge
- LLM Judge Ø
- Average quality rating by an independent judge model on a scale of 1–5.
- Coverage
- Share of tasks for which a judge rating is available. 100% means all responses were evaluated.
Latency & speed
- Avg. Task Duration
- Average time per task from the first to the last token of the response, measured across all benchmark tasks.
- Token Rate
- Output speed in tokens per second. Relevant for interactive applications and real-time streaming.
- P95 Latency
- 95th percentile of response times — shows outliers. Lower values mean fewer long wait times in edge cases.
Cost
- Cost per 1K
- API price per 1,000 output tokens in US dollars. Basis for cost calculation in production use.
- Benchmark Cost
- Total cost for the complete benchmark run of this model.