Key Takeaways
Llama 3.2 1B Instruct wins:
- Cheaper input tokens
- Cheaper output tokens
Llama 3.3 70B Instruct wins:
- Larger context window
- Faster response time
- Higher intelligence benchmark
- Better at coding
- Better at math
Price Advantage
Llama 3.2 1B Instruct
Benchmark Advantage
Llama 3.3 70B Instruct
Context Window
Llama 3.3 70B Instruct
Speed
Llama 3.3 70B Instruct
Pricing Comparison
Price Comparison
| Metric | Llama 3.2 1B Instruct | Llama 3.3 70B Instruct | Winner |
|---|---|---|---|
| Input (per 1M tokens) | $0.03 | $0.10 | Llama 3.2 1B Instruct |
| Output (per 1M tokens) | $0.20 | $0.32 | Llama 3.2 1B Instruct |
Using a 3:1 input/output ratio, Llama 3.2 1B Instruct is 55% cheaper overall.
Llama 3.2 1B Instruct Providers
Novita $0.02 (Cheapest)
Cloudflare $0.03
Llama 3.3 70B Instruct Providers
DeepInfra $0.10 (Cheapest)
Novita $0.14
Parasail $0.22
Nebius $0.25
Crusoe $0.25
Benchmark Comparison
8
Benchmarks Compared
0
Llama 3.2 1B Instruct Wins
7
Llama 3.3 70B Instruct Wins
Benchmark Scores
| Benchmark | Llama 3.2 1B Instruct | Llama 3.3 70B Instruct | Winner |
|---|---|---|---|
Intelligence Index Overall intelligence score | 9.1 | 14.2 | |
Coding Index Code generation & understanding | 0.6 | 10.7 | |
Math Index Mathematical reasoning | 0.0 | 7.7 | |
MMLU Pro Academic knowledge | 20.0 | 71.3 | |
GPQA Graduate-level science | 19.6 | 49.8 | |
LiveCodeBench Competitive programming | 1.9 | 28.8 | |
Aider Real-world code editing | - | 59.4 | - |
AIME Competition math | 0.0 | 30.0 |
Llama 3.3 70B Instruct significantly outperforms in coding benchmarks.
Cost vs Quality
X-axis:
Y-axis:
Loading chart...
Llama 3.2 1B Instruct
Other models
Context & Performance
Context Window
Llama 3.2 1B Instruct
60,000
tokens
Llama 3.3 70B Instruct
131,072
tokens
Max output: 16,384 tokens
Llama 3.3 70B Instruct has a 54% larger context window.
Speed Performance
| Metric | Llama 3.2 1B Instruct | Llama 3.3 70B Instruct | Winner |
|---|---|---|---|
| Tokens/second | 75.9 tok/s | 104.4 tok/s | |
| Time to First Token | 0.45s | 0.49s |
Llama 3.3 70B Instruct responds 37% faster on average.
Capabilities
Feature Comparison
| Feature | Llama 3.2 1B Instruct | Llama 3.3 70B Instruct |
|---|---|---|
| Vision (Image Input) | ||
| Tool/Function Calls | ||
| Reasoning Mode | ||
| Audio Input | ||
| Audio Output | ||
| PDF Input | ||
| Prompt Caching | ||
| Web Search |
License & Release
| Property | Llama 3.2 1B Instruct | Llama 3.3 70B Instruct |
|---|---|---|
| License | Open Source | Open Source |
| Author | Meta-llama | Meta-llama |
| Released | Sep 2024 | Dec 2024 |
Llama 3.2 1B Instruct Modalities
Input
text
Output
text
Llama 3.3 70B Instruct Modalities
Input
text
Output
text