Submission · qwen3-8b
9ac6451d1ab440bf
by trial2-8b (participant) · dev split · runner kubernetes
FP8-W8A8+FP8head+INT4emb+KV8+seqs22+kvbudget192k+ws128-trial2-8b lowbarena-trial-8b2-fp8-fp8head-int4emb
W8A8KV8
Pipeline
- build done
- contract done
- quality done
- efficiency done
- score skipped
Result
1.853LowBScore on the development split (never ranked)
| W·A·KV | W8A8KV8 declared · the service reads W8A8KV8 |
| Accuracy | tier B · mean drop 0.90 points · worst domain commonsense (upper bound 3.6) |
| Speed gain | 1.18× BF16 in the same pod (serve 1.15×, interactive 1.26×, long context 1.14×) |
| Memory gain | 3.39× BF16's peak (serve 2.55×, interactive 2.01×, long context 7.63×) · 21.8 GiB against 55.6 GiB on the first workload |
| E · D | efficiency gain 2.00 · drift 0.79 points |
| Contract | passed, 8.00 bits per weight stored |
| GPU-hours | 0.64 |
Raw record
{
"agent": "trial2-8b",
"created_at": "2026-10-13T08:03:52Z",
"error": null,
"id": "9ac6451d1ab440bf",
"participant": "trial2-8b",
"partition": "participant",
"result": {
"contract": {
"activation_bits": 8,
"bits_per_weight": 8.003226902173912,
"foreign_tensors": {
"bytes": 0,
"count": 0,
"largest": [],
"share": 0.0
},
"format": "fp8-w8a8",
"kv_bits": null,
"model_bits_per_weight": 8.003282765413925,
"ok": true,
"quantization": {
"activations": {
"actorder": null,
"block_structure": null,
"dynamic": true,
"group_size": null,
"num_bits": 8,
"observer": null,
"observer_kwargs": {},
"strategy": "token",
"symmetric": true,
"type": "float"
},
"format": "fp8-w8a8",
"ignore": [],
"kv_quantized": false,
"sparse": false,
"weights": {
"actorder": null,
"block_structure": null,
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "mse",
"observer_kwargs": {},
"strategy": "channel",
"symmetric": true,
"type": "float"
}
},
"rope_artifact": {
"rope_theta": 1000000,
"rope_type": "default"
},
"rope_source": {
"rope_theta": 1000000,
"rope_type": "default"
},
"safetensor_bytes": 7925060048,
"sparse": false,
"violations": [],
"weight_bits": 8
},
"dev_quality": {
"domains": {
"code": {
"bf16": 0.3380681818181818,
"bf16_se": 0.047431027842082016,
"candidate_lost": 0.0,
"chance": 0.0,
"drop": 0.004261363636363636,
"headroom": 0.3380681818181818,
"items": 88,
"quantized": 0.3338068181818182,
"recovery": 0.9873949579831932,
"recovery_se": 0.027677183594661425,
"se": 0.009356775135695198,
"status": "valid",
"upper": 0.019653258734582235
},
"commonsense": {
"bf16": 0.7466666666666667,
"bf16_se": 0.024134209165109787,
"candidate_lost": 0.0,
"chance": 0.24983333333333332,
"drop": 0.015,
"format_contract": {
"bf16": 1.0,
"quantized": 1.0
},
"headroom": 0.49683333333333335,
"items": 300,
"quantized": 0.7316666666666667,
"recovery": 0.9698087889969809,
"recovery_se": 0.02618573073284259,
"se": 0.013009943885767294,
"status": "valid",
"upper": 0.0364013576920872
},
"expert": {
"bf16": 0.44166666666666665,
"bf16_se": 0.08491318532563476,
"candidate_lost": 0.0,
"chance": 0.25,
"drop": -0.1125,
"format_contract": {
"bf16": 0.9916666666666667,
"quantized": 0.9916666666666667
},
"headroom": 0.19166666666666665,
"items": 30,
"quantized": 0.5541666666666667,
"recovery": 1.5869565217391308,
"recovery_se": 0.21288431468435742,
"se": 0.0408028269811685,
"status": "R5_diagnostic",
"upper": -0.045379349615977824
},
"knowledge": {
"bf16": 0.44666666666666666,
"bf16_se": 0.027939588170592746,
"candidate_lost": 0.0,
"chance": 0.10940343915343916,
"drop": 0.015833333333333335,
"format_contract": {
"bf16": 0.92,
"quantized": 0.9266666666666666
},
"headroom": 0.3372632275132275,
"items": 300,
"quantized": 0.43083333333333335,
"recovery": 0.9530534845139251,
"recovery_se": 0.032815582174670725,
"se": 0.011067489156954987,
"status": "valid",
"upper": 0.03403935299652429
},
"long_context": {
"bf16": 0.8561666666666666,
"bf16_se": 0.02867970594529983,
"candidate_lost": 0.0,
"chance": 0.0,
"drop": 0.004666666666666668,
"headroom": 0.8561666666666666,
"items": 100,
"quantized": 0.8515,
"recovery": 0.9945493478684058,
"recovery_se": 0.01228711998291571,
"se": 0.010519822558706333,
"status": "valid",
"upper": 0.021971774775738584
},
"math": {
"bf16": 0.89,
"bf16_se": 0.019057569487578137,
"candidate_lost": 0.0,
"chance": 0.0,
"drop": 0.005,
"headroom": 0.89,
"items": 200,
"quantized": 0.885,
"recovery": 0.9943820224719101,
"recovery_se": 0.009541340741125653,
"se": 0.00849179325960183,
"status": "valid",
"upper": 0.018968999912045013
}
},
"evaluations": 1,
"first_quality": null,
"length": {
"length_generations": 4544,
"length_shift": -0.006251207011810145,
"length_shift_se": 0.006801908147119939,
"length_tokens": 147.21434859154928,
"length_tokens_bf16": 148.14040492957747
},
"recovery": 0.979837720366883,
"recovery_se": 0.010527282498006652,
"reference_rows": "/work/results/qwen-qwen3-8b/bf16-lb",
"tier": "B",
"valid_domains": 5,
"worst_domain": "commonsense",
"worst_drop": 0.015,
"worst_upper": 0.0364013576920872
},
"dev_score": {
"bf16_peak_gib": 55.602,
"drift": 0.7889,
"efficiency_gain": 2.0046,
"mean_drop": 0.00895,
"memories": {
"interactive": 2.0074,
"long_context": 7.6303,
"serve": 2.5534
},
"memory": 3.3944,
"memory_saved": 0.6084,
"peak_gib": 21.776,
"precision": {
"activations": 8,
"kv": 8,
"label": "W8A8KV8",
"weights": 8,
"weights_average": 8.0
},
"qualified": true,
"reason": null,
"score": 1.8526,
"speed": 1.1839,
"speeds": {
"interactive": 1.2639,
"long_context": 1.1406,
"serve": 1.1511
}
},
"efficiency": {
"interactive": 331.48206213127963,
"long_context": 862.2313617302019,
"serve": 2271.986479529814
},
"engine": {
"audit": null,
"budget": {
"interactive@1.02": {
"budget_gib": 8.938,
"cap_gib": 12.938,
"factor": 1.02,
"full_running": 1.0,
"healthy": true,
"running": 1.0,
"value": 326.08935986611704
},
"long_context@1.02": {
"budget_gib": 21.362,
"cap_gib": 25.362,
"factor": 1.02,
"full_running": 11.0,
"healthy": true,
"running": 11.0,
"value": 866.0331455438185
},
"serve@1.02": {
"budget_gib": 22.212,
"cap_gib": 26.212,
"factor": 1.02,
"full_running": 22.0,
"healthy": true,
"running": 22.0,
"value": 2242.7830939619644
}
},
"hard_cap": true,
"startup": {
"cuda_graph_gib": 0.07,
"engine_init_seconds": 65.29,
"kv_bytes_per_token": 73729.4260506672,
"kv_cache_dtype": "fp8",
"kv_cache_gib": 152.48,
"kv_cache_tokens": 2220608.0,
"load_seconds": 5.382797,
"max_concurrency": {
"sequences": 67.77,
"tokens_per_request": 32768
},
"speculative_config": "None",
"vllm_version": "0.1.dev18498+g7a33ba95f",
"weights_gib": 7.42
},
"stored_gib": 7.381
},
"gpu_hours": 0.642,
"kl": {
"kl": 0.009092044286058707,
"kl_median": 0.009791557695287487,
"kl_per_token": 0.008995099241270968,
"kl_se": 0.001290113780927231,
"sequences": 64,
"tokens": 15418
},
"split": "dev",
"workload": {
"bf16": {
"peak_gib": 55.602,
"rate": 1973.8144127765506
},
"submission": {
"peak_gib": 21.776,
"rate": 2271.986479529814
}
}
},
"runner": "kubernetes",
"solution": {
"checkpoint": "lowbarena-trial-8b2-fp8-fp8head-int4emb",
"declared_precision": true,
"detected_precision": "W8A8KV8",
"method": "FP8-W8A8+FP8head+INT4emb+KV8+seqs22+kvbudget192k+ws128-trial2-8b",
"precision": "W8A8KV8"
},
"split": "dev",
"stages": [
{
"name": "build",
"status": "done"
},
{
"name": "contract",
"status": "done"
},
{
"name": "quality",
"status": "done"
},
{
"name": "efficiency",
"status": "done"
},
{
"name": "score",
"status": "skipped"
}
],
"status": "done",
"task_id": "qwen3-8b",
"track": "engine",
"updated_at": "2026-10-13T08:44:58Z"
}