docs: record Qwen MLX benchmark results
Some checks failed
CI / test (push) Has been cancelled
CI / test (pull_request) Has been cancelled

This commit is contained in:
Christian Meyer
2026-08-31 16:39:37 +02:00
parent 75b2c8958c
commit 407af8099b
40 changed files with 6091 additions and 0 deletions

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,53 @@
[
{
"task": "python_async_cache",
"runtime": "ollama",
"model": "qwen3.8:27b-mlx",
"started_at": "2026-08-31T12:05:23.192111+00:00",
"prompt_chars": 857,
"max_tokens": 3072,
"ttft_s": 1.021859125001356,
"total_s": 56.40731879102532,
"prompt_tokens": 211,
"output_tokens": 3072,
"decode_tps": 55.37840341105521,
"finish_reason": "length",
"output_chars": 12165,
"output_sha256": "a3355a481519820f9021b6846e3f784fba8aa922d3317c5a84d6762447d9dd97",
"error": null
},
{
"task": "php_idempotent_transfer",
"runtime": "ollama",
"model": "qwen3.8:27b-mlx",
"started_at": "2026-08-31T12:06:19.598953+00:00",
"prompt_chars": 756,
"max_tokens": 3072,
"ttft_s": 1.2263128339545801,
"total_s": 78.72023624996655,
"prompt_tokens": 182,
"output_tokens": 3072,
"decode_tps": 39.58218973701569,
"finish_reason": "length",
"output_chars": 12654,
"output_sha256": "070acfea480b76f0913ce21686f2031f7a32421f5645f28eebe0c2ef9d2728ec",
"error": null
},
{
"task": "typescript_dag_scheduler",
"runtime": "ollama",
"model": "qwen3.8:27b-mlx",
"started_at": "2026-08-31T12:07:38.318694+00:00",
"prompt_chars": 773,
"max_tokens": 3072,
"ttft_s": 1.5556320829782635,
"total_s": 96.54028320801444,
"prompt_tokens": 183,
"output_tokens": 3072,
"decode_tps": 32.29928081838954,
"finish_reason": "length",
"output_chars": 11211,
"output_sha256": "f97ad0b443b4fe7ae9a5b2a3f0cc3c8ad2b71bc2ba4d5849bd679b498488c654",
"error": null
}
]

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,53 @@
[
{
"task": "python_async_cache",
"runtime": "vllm-metal",
"model": "qwen3.8-27b-nvfp4",
"started_at": "2026-08-31T12:10:51.466896+00:00",
"prompt_chars": 857,
"max_tokens": 3072,
"ttft_s": 1.0361592500121333,
"total_s": 133.43742824997753,
"prompt_tokens": 211,
"output_tokens": 3072,
"decode_tps": 23.20219453486358,
"finish_reason": "length",
"output_chars": 14058,
"output_sha256": "a18e80f1852ecc0c70b987f244870b8a2dc20db8ad42505280162a4b17dbd057",
"error": null
},
{
"task": "php_idempotent_transfer",
"runtime": "vllm-metal",
"model": "qwen3.8-27b-nvfp4",
"started_at": "2026-08-31T12:13:04.907109+00:00",
"prompt_chars": 756,
"max_tokens": 3072,
"ttft_s": 15.930970875022467,
"total_s": 166.00547937501688,
"prompt_tokens": 182,
"output_tokens": 2840,
"decode_tps": 18.923933374068692,
"finish_reason": "stop",
"output_chars": 11403,
"output_sha256": "bb758808663b88bb3fbacc52df49598eb21aa8bc7fa0ee8466410f0ae13e8b0d",
"error": null
},
{
"task": "typescript_dag_scheduler",
"runtime": "vllm-metal",
"model": "qwen3.8-27b-nvfp4",
"started_at": "2026-08-31T12:15:50.913910+00:00",
"prompt_chars": 773,
"max_tokens": 3072,
"ttft_s": 1.4814700839924626,
"total_s": 152.22010587499244,
"prompt_tokens": 183,
"output_tokens": 3072,
"decode_tps": 20.379645761550783,
"finish_reason": "length",
"output_chars": 10869,
"output_sha256": "f700d51c471a59acfcf85016d416f0c5354662552fea44b48f56d80c3afdcb59",
"error": null
}
]

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,53 @@
[
{
"task": "python_async_cache",
"runtime": "ollama",
"model": "qwen3.8:27b-mxfp8",
"started_at": "2026-08-31T12:22:39.260933+00:00",
"prompt_chars": 857,
"max_tokens": 3072,
"ttft_s": 1.1107976250350475,
"total_s": 149.8235780420364,
"prompt_tokens": 211,
"output_tokens": 3072,
"decode_tps": 20.63948064778098,
"finish_reason": "length",
"output_chars": 13492,
"output_sha256": "3e5ca7654fc69293040b7cc1b554ccddbd1a99b82710d361074fee260803182f",
"error": null
},
{
"task": "php_idempotent_transfer",
"runtime": "ollama",
"model": "qwen3.8:27b-mxfp8",
"started_at": "2026-08-31T12:25:09.083177+00:00",
"prompt_chars": 756,
"max_tokens": 3072,
"ttft_s": 1.6688512500259094,
"total_s": 149.76781020802446,
"prompt_tokens": 182,
"output_tokens": 3072,
"decode_tps": 20.71737613932144,
"finish_reason": "length",
"output_chars": 12642,
"output_sha256": "71ee449c3f573828250542e04f7a63db5a8d23087bdec89f0a9a0bb31d52a3b5",
"error": null
},
{
"task": "typescript_dag_scheduler",
"runtime": "ollama",
"model": "qwen3.8:27b-mxfp8",
"started_at": "2026-08-31T12:27:38.904048+00:00",
"prompt_chars": 773,
"max_tokens": 3072,
"ttft_s": 1.6032058749697171,
"total_s": 147.27845333400182,
"prompt_tokens": 183,
"output_tokens": 3072,
"decode_tps": 21.060449812696582,
"finish_reason": "length",
"output_chars": 11368,
"output_sha256": "a3d74aa8a8183babda562bc53b32dda3b1b3ad318788d2384cc8babff3df3223",
"error": null
}
]

File diff suppressed because one or more lines are too long

View File

@@ -0,0 +1,53 @@
[
{
"task": "python_async_cache",
"runtime": "vllm-metal",
"model": "qwen3.8-27b-mxfp8",
"started_at": "2026-08-31T13:22:57.038624+00:00",
"prompt_chars": 857,
"max_tokens": 3072,
"ttft_s": 1.1419034169521183,
"total_s": 247.70563520898577,
"prompt_tokens": 211,
"output_tokens": 3072,
"decode_tps": 12.459253344652916,
"finish_reason": "length",
"output_chars": 13028,
"output_sha256": "699045091c4f5bc19d0f8f0bbc676b164512c8e3e7dec0f95acb13b5bef2f4ba",
"error": null
},
{
"task": "php_idempotent_transfer",
"runtime": "vllm-metal",
"model": "qwen3.8-27b-mxfp8",
"started_at": "2026-08-31T13:27:04.745948+00:00",
"prompt_chars": 756,
"max_tokens": 3072,
"ttft_s": 1.6236594580113888,
"total_s": 242.9034315830213,
"prompt_tokens": 182,
"output_tokens": 3072,
"decode_tps": 12.73210751545455,
"finish_reason": "length",
"output_chars": 11719,
"output_sha256": "64e2a1896826c7e6a38540d8e7d2650e66be4c3df39a3a63ca49261d90eeea17",
"error": null
},
{
"task": "typescript_dag_scheduler",
"runtime": "vllm-metal",
"model": "qwen3.8-27b-mxfp8",
"started_at": "2026-08-31T13:31:07.651240+00:00",
"prompt_chars": 773,
"max_tokens": 3072,
"ttft_s": 1.4923370420001447,
"total_s": 224.71278991695726,
"prompt_tokens": 183,
"output_tokens": 3072,
"decode_tps": 13.76217976638934,
"finish_reason": "length",
"output_chars": 10877,
"output_sha256": "bb305dfdb203bcf6d40071cb30ae92561f0b39bf38f52973d3f27e45cd5ff0a7",
"error": null
}
]