Gemma 3 270M (Unsloth)
With 270 million parameters, Gemma 3 270M is the smallest Gemma 3 model and a text-only model for local latency baselines and embedded setups. The Unsloth GGUF variant runs fully offline under the Gemma terms of use, but is not suitable as a general-purpose quality anchor.
- Restricted Weights
- Nano
- llama.cpp
- Text
- Instruction-Tuned
- Real-Time
Sovereign Risk: LOW Google DeepMind releases Gemma 3 270M as downloadable weights under the Gemma Terms of Use. Since the model is intended for fully local inference and the Unsloth GGUF build runs offline, the operational data exfiltration risk is low, although the license is restricted and not OSI-open.
Key metrics
Score · Latency · Cost · Quality
- Total Score Standard
- 23.59
- Routine
- 15.27
- Reasoning
- 8.31
- LLM Judge Avg
- 0.86 / 5
- 100 Coverage
- Avg Task Duration
- 4.18s
- Real-Time
- Token Rate
- 211.2tok/s
- Output Rate
- P95 Latency
- 5.65s
- Top 5 %
- Total Tokens
- 75400
- Output Volume
- Cost per 1K
- $0
- USD / 1K Requests
- Benchmark Cost
- $0
- Total · 75400 tok
Benchmark modules
10 modules · weighted · vs. model median & top performer
Gemma 3 270M (Unsloth)
Best model
Ø All models
Code Quality
15.2
CLI Benchmark
51.12
Logical Reasoning
17.45
UX Writing
19.85
Documentation
10.04
Content Transform.
33.8
Cultural Intelligence
31.4
Synthesis Quality
Tool Execution
ToolUse Score
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.