Llama 3.2 3B
meta/llama-3.2-3b-instruct- Meta
- Family · Llama 3
- Open weights
- Text → Text
- Tools · JSON
Not on OSMEXO yet
Spec & list price
Context128K
Max output72K
Input / 1M$0.05
Output / 1M$0.346.6× input
Usage
Tokens / day124.0M▼ 30% 7d
Usage rank#297
Requests / day36.3K
Per request · 30 days
Avg input7160.0× median
Avg output1330.2× median
Cache hit24%0.3× median
Consumption
Peak 245.2M 11 OctLow 29.2M 19 OctRank today #297
News & trends
0 mentions this week ▼ 100%this model · videos, posts, articles · 30 days
News · latest from Meta
- Meta Networking at the 2026 OCP Global Summit: Open Innovation for Scale-Up, Scale-Out, and Scale-Across AI NetworksMeta Engineering · 26 Oct
- Scale Agentic Coding Workflows with Meta’s Muse Spark Open on NVIDIA GB300 NVL72NVIDIA · 15 Oct
- Meta Muse Spark Open is live on Together AITogether AI · 15 Oct
- Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta15 Oct
Benchmarks
Benchmark data: Artificial AnalysisOutput speed#23/334158 tok/s2.4× faster than median
Fastest provider201 tok/sbest of 2 providers
First token#180.33 s3.1× quicker than median
Family progress
Intelligence Index
- Family releases7.7
Technical details
- Tokenizer
- Llama3
- Knowledge cutoff
- 2023-12-31
- License
- llama3.2
- Parameters
- 3.2B
- Moderation
- none
- Downloads · likes
- 1.0M · 2.9K
Request parameters 14
- structured_outputs
- temperature
- top_p
- top_k
- min_p
- max_tokens
- stop
- seed
- frequency_penalty
- logit_bias
+4 more
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Lightweight on-device assistants
- Low-cost classification and tagging
- Tool calling in small agents
- Structured output extraction
Think twice for
- Hard reasoning problems
- Image understanding
- Large codebase editing
Research papers
- FedSEAM: Federated Continual Learning of LLMs via Subspace Expert Agreement Merging24 Oct
- Do "True" and "False" Add Up to One? Complement Consistency in LLM-Agent Opinion Simulations23 Oct
- Compressing Onboard Language Models for Space Robots under a Behavioral-Fidelity Requirement21 Oct
- How Fine-Tuning Objectives Shape Layer-Wise Information in LLM Hallucination Detection20 Oct
- Reusing Calibration Gains across Model Representations16 Oct
- From Intent to Action: Benchmarking LLM Safety in Vehicle Voice Command Authorization17 Sep
- Do Small Models Use the Law You Give Them? Measuring Context Use on a Bilingual Bangladesh Legal Benchmark31 Aug
- It's Not the Size: Harness Design Determines Operational Stability in Small Language Models12 May
Same family
Llama 3- G
- 5.5
- 4.8
- 7.3
- 6.6
- 6.9
- 5.4
- 4.8
Want Llama 3.2 3B on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.