Llama 3.2 3B (Unsloth)
3.21B dense parameters, 128,000 tokens context: Llama 3.2 3B is Meta’s compact text-only variant of the Llama 3.2 family for local tasks such as summarization, paraphrasing, and instruction-following. Unsloth GGUF build, Llama 3.2 Community License, fully operable offline.
- Restricted Weights
- Nano
- llama.cpp
- Text
- Instruction-Tuned
- Real-Time
Sovereign Risk: LOW Meta releases Llama 3.2 under the Llama 3.2 Community License, and the Unsloth GGUF build is intended for fully local inference. The operational data exfiltration risk is low in offline operation, although the license remains restricted and not OSI-open.
Key metrics
Score · Latency · Cost · Quality
- Total Score Bronze
- 52.05
- Routine
- 32.2
- Reasoning
- 19.86
- LLM Judge Avg
- 2.37 / 5
- 100 Coverage
- Avg Task Duration
- 8.46s
- Real-Time
- Token Rate
- 55.02tok/s
- Output Rate
- P95 Latency
- 17.18s
- Top 5 %
- Total Tokens
- 52200
- Output Volume
- Cost per 1K
- $0
- USD / 1K Requests
- Benchmark Cost
- $0
- Total · 52200 tok
Benchmark modules
10 modules · weighted · vs. model median & top performer
Llama 3.2 3B (Unsloth)
Best model
Ø All models
Code Quality
46.8
CLI Benchmark
70.01
Logical Reasoning
45.05
UX Writing
54.15
Documentation
43.29
Content Transform.
60.97
Cultural Intelligence
57.3
Synthesis Quality
31.67
Tool Execution
63.33
ToolUse Score
47.83
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.