qwen-qwen3-5-35b-a3b

developer_uid: richhx
submission_id: qwen-qwen3-5-35b-a3b_v36
model_name: qwen-qwen3-5-35b-a3b_v36
model_group: Qwen/Qwen3.5-35B-A3B
status: torndown
timestamp: 2026-03-27T00:21:39+00:00
num_battles: 13666
num_wins: 6260
celo_rating: 8487.74
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: 2048
max_output_tokens: 80
reward_model: default
display_name: qwen-qwen3-5-35b-a3b_v36
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: Qwen/Qwen3.5-35B-A3B
model_size: 34B
ranking_group: single
us_pacific_date: 2026-03-23
win_ratio: 0.45807112542075223
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': ['<|endoftext|>', '\n', '<|im_end|>', '####\n', 'You:', '####', '</s>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 80}
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-v36-uploader
Waiting for job on qwen-qwen3-5-35b-a3b-v36-uploader to finish
qwen-qwen3-5-35b-a3b-v36-uploader: Using quantization_mode: none
qwen-qwen3-5-35b-a3b-v36-uploader: Downloading snapshot of Qwen/Qwen3.5-35B-A3B...
qwen-qwen3-5-35b-a3b-v36-uploader: Downloaded in 22.394s
2026-03-23T23:06:55.454807+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v36
qwen-qwen3-5-35b-a3b-v36-uploader: Processed model Qwen/Qwen3.5-35B-A3B in 49.492s
qwen-qwen3-5-35b-a3b-v36-uploader: creating bucket guanaco-vllm-models
qwen-qwen3-5-35b-a3b-v36-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v36-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
qwen-qwen3-5-35b-a3b-v36-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
qwen-qwen3-5-35b-a3b-v36-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
qwen-qwen3-5-35b-a3b-v36-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v36-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
qwen-qwen3-5-35b-a3b-v36-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v36-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
qwen-qwen3-5-35b-a3b-v36-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v36-uploader:   if re.search("-\.", bucket, re.UNICODE):
qwen-qwen3-5-35b-a3b-v36-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
qwen-qwen3-5-35b-a3b-v36-uploader:   if re.search("\.\.", bucket, re.UNICODE):
qwen-qwen3-5-35b-a3b-v36-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
qwen-qwen3-5-35b-a3b-v36-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
qwen-qwen3-5-35b-a3b-v36-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
qwen-qwen3-5-35b-a3b-v36-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
qwen-qwen3-5-35b-a3b-v36-uploader: Bucket 's3://guanaco-vllm-models/' created
qwen-qwen3-5-35b-a3b-v36-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/preprocessor_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/preprocessor_config.json
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/.gitattributes s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/.gitattributes
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/video_preprocessor_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/video_preprocessor_config.json
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/merges.txt
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/tokenizer_config.json
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors.index.json
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/vocab.json
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/LICENSE s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/LICENSE
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/config.json
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/generation_config.json
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/README.md s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/README.md
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/chat_template.jinja
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/tokenizer.json
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00014-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00014-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00009-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00009-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00003-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00003-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00013-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00013-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00002-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00002-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00007-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00007-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00010-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00010-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00001-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00001-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00011-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00011-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00005-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00005-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00012-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00012-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00004-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00004-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00006-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00006-of-00014.safetensors
qwen-qwen3-5-35b-a3b-v36-uploader: cp /dev/shm/model_output/model.safetensors-00008-of-00014.safetensors s3://guanaco-vllm-models/qwen-qwen3-5-35b-a3b-v36/default/model.safetensors-00008-of-00014.safetensors
Job qwen-qwen3-5-35b-a3b-v36-uploader completed after 83.27s with status: succeeded
Stopping job with name qwen-qwen3-5-35b-a3b-v36-uploader
Pipeline stage VLLMUploader completed in 83.95s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 2.80s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service qwen-qwen3-5-35b-a3b-v36
Waiting for inference service qwen-qwen3-5-35b-a3b-v36 to be ready
2026-03-23T23:07:55.536191+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v36
2026-03-23T23:08:55.626494+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v36
2026-03-23T23:09:55.718263+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v36
2026-03-23T23:10:55.802543+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v36
Inference service qwen-qwen3-5-35b-a3b-v36 ready after 220.60701704025269s
Pipeline stage VLLMDeployer completed in 221.13s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter-v2.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-v2.guanaco-backend.kchai-google-us-east4.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
2026-03-23T23:11:55.890225+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v36
HTTPConnectionPool(host='guanaco-submitter-v2.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-v2.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-v2.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 3.3869197368621826s
2026-03-23T23:12:55.982308+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v36
HTTPConnectionPool(host='guanaco-submitter-v2.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 0.9090206623077393s
HTTPConnectionPool(host='guanaco-submitter-v2.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-v2.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 2.3089425563812256s
2026-03-23T23:13:56.067536+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v36
Received healthy response to inference request in 9.132530689239502s
HTTPConnectionPool(host='guanaco-submitter-v2.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-v2.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 2.00748348236084s
2026-03-23T23:14:56.164035+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v36
HTTPConnectionPool(host='guanaco-submitter-v2.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 1.5445804595947266s
Received healthy response to inference request in 9.239098310470581s
Received healthy response to inference request in 1.8694071769714355s
Received healthy response to inference request in 1.6536695957183838s
HTTPConnectionPool(host='guanaco-submitter-v2.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 1.595494031906128s
Received healthy response to inference request in 1.2157435417175293s
Received healthy response to inference request in 15.033815622329712s
2026-03-23T23:15:56.263858+00:00 monitor updated for qwen-qwen3-5-35b-a3b_v36
Received healthy response to inference request in 1.0545146465301514s
Received healthy response to inference request in 1.5426292419433594s
Received healthy response to inference request in 2.112482786178589s
Received healthy response to inference request in 2.1521215438842773s
Received healthy response to inference request in 1.5267245769500732s
Received healthy response to inference request in 1.4564130306243896s
30 requests
12 failed requests
5th percentile: 1.1270676493644713
10th percentile: 1.4323460817337037
20th percentile: 1.5441902160644532
30th percentile: 1.8046859025955198
40th percentile: 2.136266040802002
50th percentile: 6.259725213050842
60th percentile: 17.065027761459344
70th percentile: 20.116637420654296
80th percentile: 20.122945737838744
90th percentile: 20.144413805007936
95th percentile: 20.156962037086487
99th percentile: 20.184065284729005
mean time: 10.045170323053997
%s, retrying in %s seconds...
Received healthy response to inference request in 1.3554692268371582s
Received healthy response to inference request in 0.9816627502441406s
Received healthy response to inference request in 1.6447041034698486s
Received healthy response to inference request in 1.2352697849273682s
Received healthy response to inference request in 1.1786651611328125s
Received healthy response to inference request in 1.2332062721252441s
Received healthy response to inference request in 1.1818087100982666s
Received healthy response to inference request in 0.8253452777862549s
Received healthy response to inference request in 0.9647748470306396s
Received healthy response to inference request in 1.137355089187622s
Received healthy response to inference request in 0.9292387962341309s
Received healthy response to inference request in 1.1295480728149414s
Received healthy response to inference request in 0.96286940574646s
Received healthy response to inference request in 1.2551372051239014s
Received healthy response to inference request in 1.310734510421753s
Received healthy response to inference request in 1.2907640933990479s
Received healthy response to inference request in 1.8193418979644775s
Received healthy response to inference request in 1.0963547229766846s
Received healthy response to inference request in 1.8865790367126465s
Received healthy response to inference request in 1.1035335063934326s
Received healthy response to inference request in 1.0055036544799805s
Received healthy response to inference request in 1.138296365737915s
Received healthy response to inference request in 1.1052353382110596s
Received healthy response to inference request in 1.308464765548706s
Received healthy response to inference request in 1.0021181106567383s
Received healthy response to inference request in 1.220381498336792s
Received healthy response to inference request in 1.2117469310760498s
Received healthy response to inference request in 1.0717322826385498s
Received healthy response to inference request in 1.2027368545532227s
Received healthy response to inference request in 1.2181875705718994s
30 requests
0 failed requests
5th percentile: 0.9443725705146789
10th percentile: 0.9645843029022216
20th percentile: 1.004826545715332
30th percentile: 1.1013798713684082
40th percentile: 1.1342322826385498
50th percentile: 1.1802369356155396
60th percentile: 1.2143231868743896
70th percentile: 1.2338253259658813
80th percentile: 1.2943042278289796
90th percentile: 1.3843927145004276
95th percentile: 1.7407548904418941
99th percentile: 1.8670802664756776
mean time: 1.2002255280812582
Pipeline stage StressChecker completed in 342.29s
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 1.97s
Shutdown handler de-registered
qwen-qwen3-5-35b-a3b_v36 status is now deployed due to DeploymentManager action
qwen-qwen3-5-35b-a3b_v36 status is now inactive due to auto deactivation removed underperforming models
qwen-qwen3-5-35b-a3b_v36 status is now torndown due to DeploymentManager action