Meta: Llama 3.2 3B Instruct

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with…

meta-llama/llama-3.2-3b-instruct

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages.

Trained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings.

Click here for the [original model card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md).

Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).

Specifications & capabilities

Input
text
Output
text
Context window · tokens
131072
Knowledge cutoff
2023-12-31
Published model ID
Llama-3.2-3B-Instruct
Capabilities
structuredOutputs
Description source ↗

Evaluations

41–60 / 69

LMArena

1,131.022

source id
lmarena
leaderboard name
LMArena Text Style Control Chinese
dimension
style
metric
Arena rating
rank
370
sample size
721
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
1105.1553909544195
confidence upper
1156.8881112758727
Original result ↗

LMArena

933.168

source id
lmarena
leaderboard name
LMArena Text Exclude Ties
dimension
general
metric
Arena rating
rank
370
sample size
5442
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
919.826349815401
confidence upper
946.5102480547648
Original result ↗

LMArena

1,142.404

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Writing And Literature And Language
dimension
style
metric
Arena rating
rank
371
sample size
2118
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
1128.2746046894658
confidence upper
1156.5341039498485
Original result ↗

LMArena

1,095.53

source id
lmarena
leaderboard name
LMArena Text Industry Writing And Literature And Language
dimension
general
metric
Arena rating
rank
371
sample size
2118
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
1081.751253600688
confidence upper
1109.3077857893588
Original result ↗

LMArena

1,017.431

source id
lmarena
leaderboard name
LMArena Text Chinese
dimension
general
metric
Arena rating
rank
371
sample size
721
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
993.0508114649313
confidence upper
1041.811829677028
Original result ↗

LMArena

1,145.947

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Business And Management And Financial Operations
dimension
style
metric
Arena rating
rank
373
sample size
1012
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
1126.0390578947936
confidence upper
1165.8541417482977
Original result ↗

LMArena

1,168.346

source id
lmarena
leaderboard name
LMArena Text Style Control Hard Prompts
dimension
style
metric
Arena rating
rank
374
sample size
2216
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
1155.7732213266402
confidence upper
1180.9180477775528
Original result ↗

LMArena

1,166.879

source id
lmarena
leaderboard name
LMArena Text Style Control Overall
dimension
style
metric
Arena rating
rank
374
sample size
7936
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
1159.1785151656725
confidence upper
1174.5799445374744
Original result ↗

LMArena

1,009.016

source id
lmarena
leaderboard name
LMArena Text Style Control Exclude Ties
dimension
style
metric
Arena rating
rank
378
sample size
5442
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
995.3078717704616
confidence upper
1022.7251177698108
Original result ↗

LMArena

1,173.847

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Software And It Services
dimension
style
metric
Arena rating
rank
379
sample size
2165
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
1160.6250222489127
confidence upper
1187.0680671713071
Original result ↗

LMArena

1,176.599

source id
lmarena
leaderboard name
LMArena Text Style Control Coding
dimension
style
metric
Arena rating
rank
380
sample size
1351
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
1160.2928591213395
confidence upper
1192.9048423018976
Original result ↗

LMArena

948.749

source id
lmarena
leaderboard name
LMArena Text Russian
dimension
general
metric
Arena rating
rank
382
sample size
933
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
926.3260530429388
confidence upper
971.1723733140739
Original result ↗

LMArena

1,088.56

source id
lmarena
leaderboard name
LMArena Text Style Control Non English
dimension
style
metric
Arena rating
rank
383
sample size
3779
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
1077.0545736443125
confidence upper
1100.0656528295785
Original result ↗

LMArena

1,005.873

source id
lmarena
leaderboard name
LMArena Text Style Control Russian
dimension
style
metric
Arena rating
rank
383
sample size
933
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
982.1187955824635
confidence upper
1029.6263738137663
Original result ↗

LMArena

1,018.761

source id
lmarena
leaderboard name
LMArena Text Non English
dimension
general
metric
Arena rating
rank
384
sample size
3779
evaluated at
2026-11-09T00:00:00.000Z
source model id
Llama 3.2 3B Instruct
confidence lower
1007.6931165640418
confidence upper
1029.8282231883036
Original result ↗

Open LLM Leaderboard v2

73.932%

source id
openLLMLeaderboardV2
leaderboard name
Open LLM v2 IFEval · Raw
dimension
instructionFollowing
metric
Raw accuracy
rank
508
aggregation scope
suite
Open LLM v2
co2_kg
1.9279617086879264
status
archived
precision
bfloat16
task_count
6
metric_kind
Raw accuracy
rank_method
Derived competition rank over published evaluations with reported scores, including variants and source flags
weight_type
Original
published_at
2025-03-20T12:17:27Z
chat_template
true
suite_version
2
model_revision
276b29ce8303c9b88966a9b32fc75692dce4d8e1
source_flagged
false
missing_metrics
    dataset_revision
    9c09a7cae43334062a82cb164f2ef255013dafa2
    metric_population
    4576
    ranking_population
    4576
    source_flag_anomaly
    false
    source model id
    meta-llama/Llama-3.2-3B-Instruct
    Original result ↗

    Open LLM Leaderboard v2

    73.932%

    source id
    openLLMLeaderboardV2
    leaderboard name
    Open LLM v2 IFEval · Normalized
    dimension
    instructionFollowing
    metric
    Normalized score
    rank
    508
    aggregation scope
    suite
    Open LLM v2
    co2_kg
    1.9279617086879264
    status
    archived
    precision
    bfloat16
    task_count
    6
    metric_kind
    Normalized score
    rank_method
    Derived competition rank over published evaluations with reported scores, including variants and source flags
    weight_type
    Original
    published_at
    2025-03-20T12:17:27Z
    chat_template
    true
    suite_version
    2
    model_revision
    276b29ce8303c9b88966a9b32fc75692dce4d8e1
    source_flagged
    false
    missing_metrics
      dataset_revision
      9c09a7cae43334062a82cb164f2ef255013dafa2
      metric_population
      4576
      ranking_population
      4576
      source_flag_anomaly
      false
      source model id
      meta-llama/Llama-3.2-3B-Instruct
      Original result ↗

      Open LLM Leaderboard v2

      17.674%

      source id
      openLLMLeaderboardV2
      leaderboard name
      Open LLM v2 MATH Lvl 5 · Normalized
      dimension
      math
      metric
      Normalized score
      rank
      1510
      aggregation scope
      suite
      Open LLM v2
      co2_kg
      1.9279617086879264
      status
      archived
      precision
      bfloat16
      task_count
      6
      metric_kind
      Normalized score
      rank_method
      Derived competition rank over published evaluations with reported scores, including variants and source flags
      weight_type
      Original
      published_at
      2025-03-20T12:17:27Z
      chat_template
      true
      suite_version
      2
      model_revision
      276b29ce8303c9b88966a9b32fc75692dce4d8e1
      source_flagged
      false
      missing_metrics
        dataset_revision
        9c09a7cae43334062a82cb164f2ef255013dafa2
        metric_population
        4576
        ranking_population
        4576
        source_flag_anomaly
        false
        source model id
        meta-llama/Llama-3.2-3B-Instruct
        Original result ↗

        Open LLM Leaderboard v2

        17.674%

        source id
        openLLMLeaderboardV2
        leaderboard name
        Open LLM v2 MATH Lvl 5 · Raw
        dimension
        math
        metric
        Raw accuracy
        rank
        1510
        aggregation scope
        suite
        Open LLM v2
        co2_kg
        1.9279617086879264
        status
        archived
        precision
        bfloat16
        task_count
        6
        metric_kind
        Raw accuracy
        rank_method
        Derived competition rank over published evaluations with reported scores, including variants and source flags
        weight_type
        Original
        published_at
        2025-03-20T12:17:27Z
        chat_template
        true
        suite_version
        2
        model_revision
        276b29ce8303c9b88966a9b32fc75692dce4d8e1
        source_flagged
        false
        missing_metrics
          dataset_revision
          9c09a7cae43334062a82cb164f2ef255013dafa2
          metric_population
          4576
          ranking_population
          4576
          source_flag_anomaly
          false
          source model id
          meta-llama/Llama-3.2-3B-Instruct
          Original result ↗

          Open LLM Leaderboard v2

          24.205%

          source id
          openLLMLeaderboardV2
          leaderboard name
          Open LLM v2 Average
          dimension
          general
          metric
          Normalized six-task average
          rank
          1768
          aggregation scope
          suite
          Open LLM v2
          co2_kg
          1.9279617086879264
          status
          archived
          precision
          bfloat16
          task_count
          6
          metric_kind
          Normalized six-task average
          rank_method
          Derived competition rank over published evaluations with reported scores, including variants and source flags
          weight_type
          Original
          published_at
          2025-03-20T12:17:27Z
          chat_template
          true
          suite_version
          2
          model_revision
          276b29ce8303c9b88966a9b32fc75692dce4d8e1
          source_flagged
          false
          missing_metrics
            dataset_revision
            9c09a7cae43334062a82cb164f2ef255013dafa2
            metric_population
            4576
            ranking_population
            4576
            source_flag_anomaly
            false
            source model id
            meta-llama/Llama-3.2-3B-Instruct
            Original result ↗

            Published prices

            1–6 / 6

            @cf/meta/llama-3.2-3b-instruct ↗

            $0.05

            Inference provider
            cloudflareWorkersAI
            Platform
            Cloudflare Workers AI
            Unit
            input_tokens_per_million
            Currency
            USD
            Billing conditions
            Billing label
            per M input tokens

            @cf/meta/llama-3.2-3b-instruct ↗

            $0.34

            Inference provider
            cloudflareWorkersAI
            Platform
            Cloudflare Workers AI
            Unit
            output_tokens_per_million
            Currency
            USD
            Billing conditions
            Billing label
            per M output tokens

            Provider specifications & access

            1–3 / 3

            llama-3.2-3b-instruct ↗

            source model id
            @cf/meta/llama-3.2-3b-instruct
            hosting
            cloudflare-hosted
            platforms
            • Cloudflare Workers AI
            context length
            80000
            architecture
            input_modalities
            • text
            output_modalities
            • text
            capabilities

              Llama-3.2-3B-Instruct ↗

              source model id
              publishers/hf-meta-llama/models/llama-3.2-3b-instruct@001
              hosting
              vertex-self-deployed
              platforms
              • Google Cloud Vertex AI
              architecture
              input_modalities
              • text
              output_modalities
              • text
              capabilities

                Llama-3.2-3B-Instruct ↗

                source model id
                publishers/meta/models/llama3-2@llama-3.2-3b-instruct
                hosting
                vertex-self-deployed
                platforms
                • Google Cloud Vertex AI
                architecture
                input_modalities
                • text
                output_modalities
                • text
                capabilities

                  Safety assessments

                  1–1 / 1

                  Foundation Model Transparency Index 2025 ↗

                  31 / 100

                  source id
                  stanfordFMTI
                  canonical model id
                  meta-llama/llama-3.2-3b-instruct
                  taxonomy
                  transparency
                  hazard category
                  transparency
                  hazard name
                  Organization transparency
                  policy area
                  Meta
                  assessment type
                  organization-level disclosure
                  metric
                  disclosure_score
                  result label
                  31 / 100
                  sample size
                  100
                  updated at
                  2026-11-09T18:08:05.227Z

                  Source specification observations

                  1–3 / 3

                  openRouter ↗

                  field
                  context_length
                  value
                  131072
                  normalized value
                  131072
                  scope
                  source-model
                  source id
                  openRouter
                  confidence
                  1

                  openRouter ↗

                  field
                  knowledge_cutoff
                  reported field
                  knowledge_cutoff
                  value
                  2023-12-31
                  normalized value
                  2023-12-31
                  precision
                  day
                  scope
                  source-model
                  source id
                  openRouter
                  confidence
                  1

                  openRouter ↗

                  field
                  max_output_tokens
                  value
                  72000
                  normalized value
                  72000
                  scope
                  source-model
                  source id
                  openRouter
                  confidence
                  1

                  Original sources

                  1–19 / 19

                  Hugging Face · Model repository ↗

                  Cloudflare AI · Model page ↗

                  DeepInfra · Model page ↗

                  Google Cloud · Model page ↗

                  Google Cloud · Model page ↗

                  OpenRouter · Model page ↗

                  arXiv · Paper · 2204.05149 ↗

                  arXiv · Paper · 2405.16406 ↗

                  GitHub · Source snapshot ↗

                  Cloudflare AI · Catalog ↗

                  DeepInfra · Catalog ↗

                  GitHub · Catalog ↗

                  GitHub · Catalog ↗

                  Google Cloud · Catalog ↗

                  Hugging Face · Catalog ↗

                  Hugging Face · Catalog ↗

                  LMArena · Catalog ↗

                  OpenRouter · Catalog ↗

                  OpenRouter · Catalog ↗

                  Source links

                  1–11 / 11

                  Hugging Face model card

                  1–1 / 1

                  Explore more models

                  Models

                  Loading
                  EVIDENCE / COMPARISON

                  Benchmarks

                  Explore every benchmark

                  Loading

                  These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

                  Install TensorTrace