qwen-qwen3-5-35b-a3b

developer_uid: richhx
submission_id: qwen-qwen3-5-35b-a3b_v33
model_name: qwen-qwen3-5-35b-a3b_v33
model_group: Qwen/Qwen3.5-35B-A3B
status: torndown
timestamp: 2026-03-25T06:27:04+00:00
num_battles: 10873
num_wins: 4390
celo_rating: 1225.0
family_friendly_score: 0.0
family_friendly_standard_error: 0.0
submission_type: basic
model_repo: Qwen/Qwen3.5-35B-A3B
model_architecture: Qwen3_5MoeForConditionalGeneration
model_num_parameters: 33753909248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
display_name: qwen-qwen3-5-35b-a3b_v33
is_internal_developer: True
language_model: Qwen/Qwen3.5-35B-A3B
model_size: 34B
ranking_group: single
us_pacific_date: 2026-03-21
win_ratio: 0.40375241423710106
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['####\n', '</s>', 'You:', '####', '<|endoftext|>', '<|im_end|>', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}</s>\n', 'user_template': 'You: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Starting job with name qwen-qwen3-5-35b-a3b-v33-uploader
Waiting for job on qwen-qwen3-5-35b-a3b-v33-uploader to finish
qwen-qwen3-5-35b-a3b-v33-uploader: Using quantization_mode: none
qwen-qwen3-5-35b-a3b-v33-uploader: Downloading snapshot of Qwen/Qwen3.5-35B-A3B...
qwen-qwen3-5-35b-a3b-v33-uploader: Downloaded in 21.981s
2026-03-22T03:33:24.561272+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v33
qwen-qwen3-5-35b-a3b-v33-uploader: Processed model Qwen/Qwen3.5-35B-A3B in 48.932s
qwen-qwen3-5-35b-a3b-v33-uploader: creating bucket guanaco-vllm-models
qwen-qwen3-5-35b-a3b-v33-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v33-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
qwen-qwen3-5-35b-a3b-v33-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
qwen-qwen3-5-35b-a3b-v33-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
qwen-qwen3-5-35b-a3b-v33-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v33-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
qwen-qwen3-5-35b-a3b-v33-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v33-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
qwen-qwen3-5-35b-a3b-v33-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v33-uploader:   if re.search("-\.", bucket, re.UNICODE):
qwen-qwen3-5-35b-a3b-v33-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v33-uploader:   if re.search("\.\.", bucket, re.UNICODE):
qwen-qwen3-5-35b-a3b-v33-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
qwen-qwen3-5-35b-a3b-v33-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
qwen-qwen3-5-35b-a3b-v33-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
qwen-qwen3-5-35b-a3b-v33-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
qwen-qwen3-5-35b-a3b-v33-uploader: Bucket 's3://guanaco-vllm-models/' created
qwen-qwen3-5-35b-a3b-v33-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/preprocessor_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/preprocessor_config.json
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/.gitattributes
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/generation_config.json
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/README.md
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/config.json
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/video_preprocessor_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/video_preprocessor_config.json
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/chat_template.jinja
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/LICENSE s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/LICENSE
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors.index.json
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/tokenizer_config.json
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/merges.txt
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/vocab.json
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/tokenizer.json
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00014-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00014-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00010-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00010-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00004-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00004-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00005-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00005-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00012-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00012-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00002-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00002-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00001-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00001-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00007-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00007-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00009-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00009-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00003-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00003-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00011-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00011-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00008-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00008-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00006-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00006-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v33-uploader: cp /dev/shm/model_output/model.safetensors-00013-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v33/default/model.safetensors-00013-of-00014.safetensors
Job qwen-qwen3-5-35b-a3b-v33-uploader completed after 84.03s with status: succeeded
Stopping job with name qwen-qwen3-5-35b-a3b-v33-uploader
Pipeline stage VLLMUploader completed in 84.53s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 2.72s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service qwen-qwen3-5-35b-a3b-v33
Waiting for inference service qwen-qwen3-5-35b-a3b-v33 to be ready
2026-03-22T03:34:24.683496+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v33
2026-03-22T03:35:24.787927+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v33
2026-03-22T03:36:24.901802+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v33
Inference service qwen-qwen3-5-35b-a3b-v33 ready after 210.59159755706787s
Pipeline stage VLLMDeployer completed in 211.21s
run pipeline stage %s
Running pipeline stage StressChecker
2026-03-22T03:37:25.008334+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v33
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-22T03:38:25.175482+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v33
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 3.744933843612671s
Received healthy response to inference request in 6.754842042922974s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-22T03:39:25.286557+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v33
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.5372345447540283s
Received healthy response to inference request in 4.3371734619140625s
Received healthy response to inference request in 1.5540657043457031s
Received healthy response to inference request in 0.9635686874389648s
Received healthy response to inference request in 1.6134507656097412s
Received healthy response to inference request in 1.0103721618652344s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.0170094966888428s
Received healthy response to inference request in 1.2174365520477295s
Received healthy response to inference request in 1.677687644958496s
Received healthy response to inference request in 2.4370319843292236s
Received healthy response to inference request in 1.0199744701385498s
Received healthy response to inference request in 2.8823304176330566s
2026-03-22T03:40:25.726348+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v33
Received healthy response to inference request in 1.4938406944274902s
Received healthy response to inference request in 1.8061447143554688s
Received healthy response to inference request in 1.5842993259429932s
Received healthy response to inference request in 1.21474289894104s
Received healthy response to inference request in 1.189873456954956s
Received healthy response to inference request in 0.9706437587738037s
Received healthy response to inference request in 1.4082317352294922s
Received healthy response to inference request in 1.0611231327056885s
Received healthy response to inference request in 1.7075278759002686s
30 requests
7 failed requests
5th percentile: 0.9885215401649475
10th percentile: 1.0163457632064818
20th percentile: 1.1641233921051026
30th percentile: 1.3509931802749633
40th percentile: 1.5473332405090332
50th percentile: 1.6455692052841187
60th percentile: 2.0584996223449696
70th percentile: 3.9226057291030867
80th percentile: 20.12354850769043
90th percentile: 20.144202446937562
95th percentile: 20.145452475547792
99th percentile: 20.146454486846924
mean time: 6.172247656186422
%s, retrying in %s seconds...
Received healthy response to inference request in 1.8555960655212402s
Received healthy response to inference request in 0.8479876518249512s
Received healthy response to inference request in 0.9683070182800293s
Received healthy response to inference request in 0.935175895690918s
Received healthy response to inference request in 0.7306599617004395s
Received healthy response to inference request in 0.9128940105438232s
Received healthy response to inference request in 1.0182008743286133s
Received healthy response to inference request in 1.1900229454040527s
Received healthy response to inference request in 1.030841588973999s
Received healthy response to inference request in 0.958371639251709s
Received healthy response to inference request in 1.324497938156128s
Received healthy response to inference request in 0.8623471260070801s
Received healthy response to inference request in 1.6858305931091309s
Received healthy response to inference request in 0.7977313995361328s
Received healthy response to inference request in 0.9580557346343994s
Received healthy response to inference request in 1.185969352722168s
Received healthy response to inference request in 1.0218665599822998s
Received healthy response to inference request in 1.0180070400238037s
Received healthy response to inference request in 1.2251272201538086s
Received healthy response to inference request in 1.316084623336792s
Received healthy response to inference request in 1.0382773876190186s
Received healthy response to inference request in 0.9671366214752197s
Received healthy response to inference request in 1.302274465560913s
Received healthy response to inference request in 1.0974986553192139s
Received healthy response to inference request in 0.9158267974853516s
Received healthy response to inference request in 1.2117269039154053s
Received healthy response to inference request in 1.107726812362671s
Received healthy response to inference request in 1.109189748764038s
Received healthy response to inference request in 0.924166202545166s
Received healthy response to inference request in 1.1790425777435303s
30 requests
0 failed requests
5th percentile: 0.8203467130661011
10th percentile: 0.8609111785888672
20th percentile: 0.9224983215332031
30th percentile: 0.9582768678665161
40th percentile: 0.998127031326294
50th percentile: 1.0263540744781494
60th percentile: 1.1015899181365967
70th percentile: 1.1811206102371217
80th percentile: 1.214406967163086
90th percentile: 1.3169259548187255
95th percentile: 1.5232308983802785
99th percentile: 1.8063640785217288
mean time: 1.0898813803990681
Pipeline stage StressChecker completed in 234.45s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 1.19s
Shutdown handler de-registered
qwen-qwen3-5-35b-a3b_v33 status is now deployed due to DeploymentManager action
qwen-qwen3-5-35b-a3b_v33 status is now inactive due to auto deactivation removed underperforming models
qwen-qwen3-5-35b-a3b_v33 status is now torndown due to DeploymentManager action