Meta model product
Llama 3.2 3B
2 3B Instruct is a large language model with a 128K-token context length for local edge use cases such as summarization, instruction following, and rewriting.
Updated Sep 8, 2026. Default version: Llama 3.2 3B Instruct
LLMBoard Score0.0Llama 3.2 3B Instruct
Coverage40%10 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
Llama 3.2 3B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Llama 3.2 3B Benchmark Results
Benchmark scores for Llama 3.2 3B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkInfiniteBench/En.MC | Score63.30% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkInfiniteBench/En.QA | Score19.80% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkNIH/Multi-needle | Score84.70% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOpen-rewrite | Score40.10% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTLDR9+ (test) | Score19.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBFCL v2 | Score67.00% | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkNexus | Score34.30% | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score78.60% | Rank17 | Participants34 | Percentile51.52% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score69.80% | Rank24 | Participants27 | Percentile11.54% | EvidenceC | Evaluated |
| BenchmarkMGSM | Score58.20% | Rank27 | Participants31 | Percentile13.33% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score77.70% | Rank40 | Participants48 | Percentile17.02% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score77.40% | Rank58 | Participants68 | Percentile14.93% | EvidenceC | Evaluated |
| BenchmarkMATH | Score48.00% | Rank60 | Participants71 | Percentile15.71% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score63.40% | Rank96 | Participants101 | Percentile5.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,166.29 rating | Rank209 | Participants210 | Percentile0.48% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,109.31 rating | Rank210 | Participants210 | Percentile0.00% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score32.80% | Rank232 | Participants247 | Percentile6.10% | EvidenceC | Evaluated |
Llama 3.2 3B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categorygerman | Rank181 | Rating / score1,055.88 | Votes232 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank181 | Rating / score1,109.80 | Votes232 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank201 | Rating / score1,128.43 | Votes980 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank202 | Rating / score1,017.17 | Votes721 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank202 | Rating / score1,125.89 | Votes1,136 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank202 | Rating / score1,129.71 | Votes721 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank202 | Rating / score1,173.99 | Votes980 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank202 | Rating / score1,164.92 | Votes1,136 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank204 | Rating / score1,103.62 | Votes441 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank205 | Rating / score1,202.37 | Votes441 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank206 | Rating / score1,090.21 | Votes499 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank206 | Rating / score1,188.47 | Votes506 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank207 | Rating / score1,115.26 | Votes506 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank207 | Rating / score1,178.06 | Votes499 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank208 | Rating / score1,179.59 | Votes4,157 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts english | Rank208 | Rating / score1,140.95 | Votes1,377 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank209 | Rating / score1,093.99 | Votes1,070 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank209 | Rating / score1,105.84 | Votes1,355 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank209 | Rating / score1,176.35 | Votes1,351 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank209 | Rating / score1,144.01 | Votes1,070 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank209 | Rating / score1,224.36 | Votes4,157 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank209 | Rating / score1,208.02 | Votes1,377 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank209 | Rating / score1,145.61 | Votes1,012 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank209 | Rating / score1,141.37 | Votes1,149 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank209 | Rating / score1,185.00 | Votes1,355 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank209 | Rating / score1,173.87 | Votes2,165 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank209 | Rating / score1,141.68 | Votes2,118 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank209 | Rating / score1,149.09 | Votes1,299 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank209 | Rating / score1,166.29 | Votes7,936 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank210 | Rating / score1,098.02 | Votes1,351 | ObservationsN/A | Result date |
Llama 3.2 3B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.02 input, $0.02 output per 1M via Inference
- Tracked offerings
- 10
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNvidia | Provider model IDmeta/llama-3.2-3b-instruct | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context32.8K | Updated |
| ProviderInference | Provider model IDmeta/llama-3.2-3b-instruct | Regionglobal | Input / 1M$0.02 | Output / 1M$0.02 | Context16K | Updated |
| ProviderNovitaAI | Provider model IDmeta-llama/llama-3.2-3b-instruct | Regionglobal | Input / 1M$0.03 | Output / 1M$0.05 | Context32.8K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDllama-3.2-3b-instruct | Regionglobal | Input / 1M$0.03 | Output / 1M$0.05 | Context32.8K | Updated |
| ProviderNanoGPT | Provider model IDmeta-llama/llama-3.2-3b-instruct | Regionglobal | Input / 1M$0.0306 | Output / 1M$0.0493 | Context131.1K | Updated |
| ProviderOpenRouter | Provider model IDmeta-llama/llama-3.2-3b-instruct | Regionglobal | Input / 1M$0.05 | Output / 1M$0.33 | Context131.1K | Updated |
| ProviderCloudflare Workers AI | Provider model ID@cf/meta/llama-3.2-3b-instruct | Regionglobal | Input / 1M$0.0509 | Output / 1M$0.335 | Context80K | Updated |
| ProviderPioneer | Provider model IDmeta-llama/Llama-3.2-3B | Regionglobal | Input / 1M$0.10 | Output / 1M$0.10 | Context131.1K | Updated |
| ProviderPioneer | Provider model IDmeta-llama/Llama-3.2-3B-Instruct | Regionglobal | Input / 1M$0.10 | Output / 1M$0.335 | Context131.1K | Updated |
| ProviderVenice AI | Provider model IDllama-3.2-3b | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Llama 3.2 3B Runtime Performance
Provider-specific output speed and catalog latency for Llama 3.2 3B Instruct. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderDeepInfra | Output Speed171.50 tok/s | Catalog Latency0.24 s | Max Input128K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Llama 3.2 3B Specifications
Technical details for the model's default version.
- Version
- Llama 3.2 3B Instruct
- Released
- Sep 25, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 3.2B
- Context window
- 128K
- Max output
- 128K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Llama 3.2 Community License
Llama 3.2 3B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionLlama 3.2 3B Instruct | Released | LLMBoard0.00 | Parameters3.2B | Context128K | Max output128K | Open weightsYes | LicenseLlama 3.2 Community License |
Models similar to Llama 3.2 3B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ME
Llama 3.1 8B
Meta
ME
Llama 3.2 11B
Meta
ME
Llama 3.2 90B
Meta
ME
Llama 3.1 70B
Meta
ME
Llama 4 Scout
Meta
ME
Llama 3.3 70B
Meta
What is Llama 3.2 3B?
Key information about Llama 3.2 3B and its available data.
2 3B Instruct is a Meta large language model designed for on-device use cases. It supports a context length of 128K tokens and can be used for summarization, instruction following, and rewriting tasks running locally at the edge.
Data as of 2026-09-08.
FAQ
Common questions about Llama 3.2 3B.
When was Llama 3.2 3B released?
Llama 3.2 3B's default version was released on Sep 25, 2024.
How much does Llama 3.2 3B cost?
No official standard PAYG price is currently available for Llama 3.2 3B. The lowest tracked third-party offer starts at $0.02 input and $0.02 output via Inference.
Who created Llama 3.2 3B?
Llama 3.2 3B was created by Meta.
What is the context window for Llama 3.2 3B?
The default version has a 128K token context window.
Is Llama 3.2 3B open weight?
Yes. The default version is marked as open weight under Llama 3.2 Community License.
How many API providers offer Llama 3.2 3B?
10 provider offerings are linked to the default version.