Llama 3.3 Nemotron Super 49B v1.5
NVIDIA Llama 3.3 Nemotron Super 49B v1.5 is a pruning- and distillation-optimized variant of Meta’s Llama 3.3 70B with 49 billion parameters. The model delivers strong reasoning performance at reduced resource requirements, a context window of 131,000 tokens, and an optional thinking mode controlled via system prompt. Available as an Open Weights variant under the NVIDIA Open Model License, locally or through cloud providers.
- Open Weights
- Server
- OR
- Text
- Instruction-Tuned
- Interactive
Key metrics
Score · Latency · Cost · Quality
- Total Score Silver
- 70.2
- Routine
- 42.89
- Reasoning
- 27.31
- LLM Judge Avg
- 3.49 / 5
- 100 Coverage
- Avg Task Duration
- 36.91s
- Interactive
- Token Rate
- 20.73tok/s
- Output Rate
- P95 Latency
- 83.14s
- Top 5 %
- Total Tokens
- 105100
- Output Volume
- Cost per 1K
- $0.0004
- USD / 1K Requests
- Benchmark Cost
- $0.04
- Total · 105100 tok
Benchmark modules
10 modules · weighted · vs. model median & top performer
Llama 3.3 Nemotron Super 49B v1.5
Best model
Ø All models
Code Quality
66
CLI Benchmark
80.34
Logical Reasoning
66.22
UX Writing
68.69
Documentation
64.72
Content Transform.
76.5
Cultural Intelligence
71.72
Synthesis Quality
55.83
Tool Execution
90
ToolUse Score
72.92
Benchmark Cost
$0.04
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).
- 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.