Model Library
MetaReleased September 25, 2024Llama 3.2 3B
Meta · Released September 25, 2024
Intelligence score
4
At a glance
- Intelligence
- 4
- Speed
- 51.8tokens/sec
- Latency
- 1.07stime to first token
- Input price
- $0.15per 1M tokens
- Output price
- $0.15per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 3billions
Summary
Comparison summary
Llama 3.2 Instruct 3B scores 4 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 3). Llama 3.2 Instruct 3B generates output at 51.8 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight non-reasoning models of similar size (median: 85.1 t/s). Llama 3.2 Instruct 3B costs $0.15 per 1M input tokens (at the higher end, median: $0.11) and $0.15 per 1M output tokens (better than average, median: $0.28), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Llama 3.2 3B |
|---|---|
| Provider | Meta |
| Release date | September 25, 2024 |
| Intelligence score | 4 |
| Speed | 51.8 tokens/sec |
| Latency (TTFT) | 1.07s |
| Input price | $0.15 / 1M tokens |
| Output price | $0.15 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 3B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | LLAMA 3 |
| API availability | — |
| Source | Model Intelligence legacy profile: llama-3-2-instruct-3b |
Pricing
Token prices
Price per 1M tokens
Llama 3.2 3B, as listed in the catalog record
- Input$0.15
- Output$0.15
| Token type | Price per 1M |
|---|---|
| Input | $0.15 |
| Output | $0.15 |
Model Intelligence legacy profile: llama-3-2-instruct-3b
FAQ · 20
Frequently asked questions
Llama 3.2 Instruct 3B was released on September 25, 2024.
Llama 3.2 Instruct 3B was created by Meta.
Llama 3.2 Instruct 3B scores 4 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 3).
Llama 3.2 Instruct 3B generates output at 51.8 tokens per second (based on the median across providers serving the model), which is below average compared to other open weight non-reasoning models of similar size (median: 85.1 t/s).
Llama 3.2 Instruct 3B has a time to first token (TTFT) of 1.07s (based on the median across providers serving the model), which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 0.84s).
Llama 3.2 Instruct 3B costs $0.15 per 1M input tokens (at the higher end, median: $0.11) and $0.15 per 1M output tokens (better than average, median: $0.28), based on the median across providers serving the model.
Llama 3.2 Instruct 3B costs $0.15 per 1M input tokens and $0.15 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.15 per 1M tokens. Pricing may vary by provider.
No, Llama 3.2 Instruct 3B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Llama 3.2 Instruct 3B supports text only input.
Llama 3.2 Instruct 3B supports text only output.
No, Llama 3.2 Instruct 3B does not support image input. It can only process text.
No, Llama 3.2 Instruct 3B is not multimodal. It only supports text only input.
Llama 3.2 Instruct 3B has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Llama 3.2 Instruct 3B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Llama 3.2 Instruct 3B has 3 billion parameters.
Llama 3.2 Instruct 3B is released under the LLAMA 3.2 COMMUNITY LICENSE AGREEMENT license. This license allows commercial use.
Llama 3.2 Instruct 3B achieves a score of 4 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Llama 3.2 Instruct 3B has a knowledge cutoff of December 2023. The model's training data includes information up to this date.
Yes, Llama 3.2 Instruct 3B is available via API through 1 provider.
Llama 3.2 Instruct 3B is available through 1 API provider.