Qwen/Qwen1.5-32B-Chat

`Qwen/Qwen1.5-32B-Chat` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingf…

azureFoundry/HuggingFace/qwen-qwen1.5-32b-chat@1

Qwen/Qwen1.5-32B-Chat powered by Text Generation Inference (TGI)

Send Request

You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token.

curl <AZUREML_ENDPOINT_URL> \
    -X POST \
    -d '{"inputs":"What is Deep Learning?"}' \
    -H "Authorization: Bearer <AZUREML_TOKEN>" \
    -H "Content-Type: application/json"

Supported Parameters

  • inputs (string): Input prompt.
  • parameters (object):
    • best_of (integer): Generate best_of sequences and return the one if the highest token logprobs.
    • decoder_input_details (boolean): Whether to return decoder input token logprobs and ids.
    • details (boolean): Whether to return generation details.
    • do_sample (boolean): Activate logits sampling.
    • frequency_penalty (float): The parameter for frequency penalty. 1.0 means no penalty Penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.
    • grammar (object): One of the following
      • #1 (object):
        • type (enum): Possible values: json.
        • value (string): A string that represents a JSON Schema. JSON Schema is a declarative language that allows to annotate JSON documents with types and descriptions.
      • #2 (object):
        • type (enum): Possible values: regex.
        • value (string): The regular expression.
      • #3 (object):
        • type (enum): Possible values: json_schema.
        • value (object):
          • name (string): Optional name identifier for the schema
          • schema (object): The actual JSON schema definition
    • max_new_tokens (integer): Maximum number of tokens to generate.
    • repetition_penalty (float): The parameter for repetition penalty. 1.0 means no penalty. See this paper for more details.
    • return_full_text (boolean): Whether to prepend the prompt to the generated text
    • seed (integer): Random sampling seed.
    • stop (string[]): Stop generating tokens if a member of stop is generated.
    • temperature (float): The value used to module the logits distribution.
    • top_k (integer): The number of highest probability vocabulary tokens to keep for top-k-filtering.
    • top_n_tokens (integer): The number of highest probability vocabulary tokens to keep for top-n-filtering.
    • top_p (float): Top-p value for nucleus sampling.
    • truncate (integer): Truncate inputs tokens to the given size.
    • typical_p (float): Typical Decoding mass See Typical Decoding for Natural Language Generation for more information.
    • watermark (boolean): Watermarking with A Watermark for Large Language Models.
    • stream (boolean): Whether to stream the output tokens or not. Defaults to false.

Example payload

{
  "inputs": "What is Deep Learning?",
  "parameters": {
    "do_sample": true,
    "top_p": 0.95,
    "temperature": 0.2,
    "top_k": 50,
    "max_new_tokens": 256,
    "repetition_penalty": 1.03,
    "stop": ["\nUser:", "<|endoftext|>", "</s>"]
  }
}

OpenAI Chat Completion API compatibility

Additionally, Text Generation Inference (TGI) offers an OpenAI Chat Completion API compatible layer under the endpoint /v1/chat/completions, check the full specification in the OpenAI Chat Completion Create Documentation.

Specifications & capabilities

Input
text
Output
text
Published model ID
Qwen1.5-32B-Chat

Evaluations

1–20 / 76

Open LLM Leaderboard v1

74.993%

source id
openLLMLeaderboardV1
leaderboard name
Open LLM v1 MMLU
dimension
knowledge
metric
Accuracy
rank
259
aggregation scope
suite
Open LLM v1
status
archived
precision
bfloat16
task_count
6
metric_kind
Accuracy
rank_method
Derived competition rank over published evaluations with reported scores, including variants and source flags
weight_type
Original
published_at
2024-06-25T14:11:42Z
chat_template
false
suite_version
1
model_revision
0b1785d88bbe93aa90a8a19da8af78eccbf010a6
source_flagged
true
missing_metrics
    dataset_revision
    791ca1c841030008c6c266562c2b88c9b7196550
    metric_population
    7260
    ranking_population
    7260
    source_flag_anomaly
    true
    evaluated at
    2024-04-05T21:01:12.000Z
    source model id
    Qwen/Qwen1.5-32B-Chat
    Original result ↗

    LMArena

    1,100.218

    source id
    lmarena
    leaderboard name
    LMArena Text Style Control Japanese
    dimension
    style
    metric
    Arena rating
    rank
    265
    sample size
    324
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1065.9553602330352
    confidence upper
    1134.4803706611804
    Original result ↗

    LMArena

    1,027.453

    source id
    lmarena
    leaderboard name
    LMArena Text Japanese
    dimension
    general
    metric
    Arena rating
    rank
    265
    sample size
    324
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    993.6320120551495
    confidence upper
    1061.2745742019974
    Original result ↗

    LMArena

    1,007.71

    source id
    lmarena
    leaderboard name
    LMArena Text Korean
    dimension
    general
    metric
    Arena rating
    rank
    274
    sample size
    395
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    976.1123362087378
    confidence upper
    1039.3069969292378
    Original result ↗

    LMArena

    1,094.984

    source id
    lmarena
    leaderboard name
    LMArena Text Style Control Korean
    dimension
    style
    metric
    Arena rating
    rank
    275
    sample size
    395
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1062.1590845904002
    confidence upper
    1127.8097747395452
    Original result ↗

    LMArena

    1,100.394

    source id
    lmarena
    leaderboard name
    LMArena Text French
    dimension
    general
    metric
    Arena rating
    rank
    283
    sample size
    313
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1065.0740479147391
    confidence upper
    1135.7146212028124
    Original result ↗

    LMArena

    1,177.325

    source id
    lmarena
    leaderboard name
    LMArena Text Style Control French
    dimension
    style
    metric
    Arena rating
    rank
    285
    sample size
    313
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1142.0481102180613
    confidence upper
    1212.601487102195
    Original result ↗

    LMArena

    1,168.273

    source id
    lmarena
    leaderboard name
    LMArena Text Style Control Spanish
    dimension
    style
    metric
    Arena rating
    rank
    290
    sample size
    369
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1136.1452463902328
    confidence upper
    1200.4005415293136
    Original result ↗

    LMArena

    1,088.781

    source id
    lmarena
    leaderboard name
    LMArena Text Spanish
    dimension
    general
    metric
    Arena rating
    rank
    290
    sample size
    369
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1057.0348047204593
    confidence upper
    1120.5275500872106
    Original result ↗

    LMArena

    1,058.148

    source id
    lmarena
    leaderboard name
    LMArena Text German
    dimension
    general
    metric
    Arena rating
    rank
    300
    sample size
    777
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1035.2768067707061
    confidence upper
    1081.0185385732807
    Original result ↗

    LMArena

    1,128.167

    source id
    lmarena
    leaderboard name
    LMArena Text Style Control German
    dimension
    style
    metric
    Arena rating
    rank
    301
    sample size
    777
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1105.191348331904
    confidence upper
    1151.1425086926101
    Original result ↗

    LMArena

    1,267.144

    source id
    lmarena
    leaderboard name
    LMArena Text Style Control Chinese
    dimension
    style
    metric
    Arena rating
    rank
    313
    sample size
    3241
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1253.6174447502835
    confidence upper
    1280.6715102707258
    Original result ↗

    LMArena

    1,176.681

    source id
    lmarena
    leaderboard name
    LMArena Text Chinese
    dimension
    general
    metric
    Arena rating
    rank
    323
    sample size
    3241
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1163.3261521875993
    confidence upper
    1190.0354325133248
    Original result ↗

    LMArena

    1,223.936

    source id
    lmarena
    leaderboard name
    LMArena Text Style Control Expert
    dimension
    style
    metric
    Arena rating
    rank
    325
    sample size
    1176
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1205.818191859111
    confidence upper
    1242.0539949568033
    Original result ↗

    LMArena

    1,125.819

    source id
    lmarena
    leaderboard name
    LMArena Text Expert
    dimension
    general
    metric
    Arena rating
    rank
    328
    sample size
    1176
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1107.7046921226142
    confidence upper
    1143.9326144942243
    Original result ↗

    LMArena

    1,215.487

    source id
    lmarena
    leaderboard name
    LMArena Text Style Control Industry Mathematical
    dimension
    style
    metric
    Arena rating
    rank
    329
    sample size
    2405
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1202.9131856767804
    confidence upper
    1228.0610689917085
    Original result ↗

    LMArena

    1,162.676

    source id
    lmarena
    leaderboard name
    LMArena Text Industry Mathematical
    dimension
    general
    metric
    Arena rating
    rank
    331
    sample size
    2405
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1150.1562854192866
    confidence upper
    1175.1962062445443
    Original result ↗

    LMArena

    1,201.302

    source id
    lmarena
    leaderboard name
    LMArena Text Style Control Math
    dimension
    style
    metric
    Arena rating
    rank
    332
    sample size
    2649
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1189.5993342840911
    confidence upper
    1213.0045437557483
    Original result ↗

    LMArena

    1,155.065

    source id
    lmarena
    leaderboard name
    LMArena Text Math
    dimension
    general
    metric
    Arena rating
    rank
    332
    sample size
    2649
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1143.3765296600332
    confidence upper
    1166.7539029978689
    Original result ↗

    LMArena

    1,227.553

    source id
    lmarena
    leaderboard name
    LMArena Text Style Control Industry Legal And Government
    dimension
    style
    metric
    Arena rating
    rank
    337
    sample size
    1227
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    Qwen1.5-32B-Chat
    confidence lower
    1209.6137359016248
    confidence upper
    1245.491552513199
    Original result ↗

    Provider specifications & access

    1–1 / 1

    Qwen/Qwen1.5-32B-Chat ↗

    source model id
    HuggingFace/qwen-qwen1.5-32b-chat@1
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    license
    other
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      Safety assessments

      1–1 / 1

      Foundation Model Transparency Index 2025 ↗

      26 / 100

      source id
      stanfordFMTI
      canonical model id
      azureFoundry/HuggingFace/qwen-qwen1.5-32b-chat@1
      taxonomy
      transparency
      hazard category
      transparency
      hazard name
      Organization transparency
      policy area
      Alibaba
      assessment type
      organization-level disclosure
      metric
      disclosure_score
      result label
      26 / 100
      sample size
      100
      updated at
      2026-11-09T18:08:05.227Z

      Original sources

      1–8 / 8

      Hugging Face · Model repository ↗

      Microsoft Foundry · Model page ↗

      Microsoft Foundry · Model documentation ↗

      GitHub · Catalog ↗

      Hugging Face · Catalog ↗

      Hugging Face · Catalog ↗

      LMArena · Catalog ↗

      Microsoft Foundry · Catalog ↗

      Source links

      1–5 / 5

      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