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 +1,8 @@
run_id,runtime,model,phase,concurrency,round,slot,request_id,prompt_name,prompt_chars,max_tokens,started_at,ttft_s,total_s,prompt_tokens,output_tokens,prompt_tps,decode_tps,request_tps,group_elapsed_s,group_output_tps,error
20260831T134334Z,ollama,qwen3.8:27b-mlx,warmup,1,0,0,c3b04207-976b-4a0d-9d3c-80ef8dc4225f,short,106,128,2026-08-31T13:43:39.472249+00:00,3.4916902080294676,5.4140321660088375,20,96,114.72541286980045,48.19996255746575,17.731701079044402,5.4149448340176605,17.728712469407014,
20260831T134334Z,ollama,qwen3.8:27b-mlx,warmup,1,1,0,47d529a2-f167-46a0-af05-a6ca0e1929a4,medium,252,128,2026-08-31T13:43:44.886979+00:00,0.35504300001775846,2.7301927499938756,43,128,157.93211765391837,52.61516193511847,46.88313673101913,2.730699084000662,46.87444352618714,
20260831T134334Z,ollama,qwen3.8:27b-mlx,measured,1,0,0,5b638c8b-a185-48d7-8625-f6ebacc06853,short,106,128,2026-08-31T13:43:47.617556+00:00,0.11980204097926617,2.1940376659622416,20,96,441.616869764425,45.28260592046214,43.7549461840698,2.1943347500055097,43.749022340260055,
20260831T134334Z,ollama,qwen3.8:27b-mlx,measured,1,1,0,fd1c62de-2412-4243-85a0-0851e2364f7c,medium,252,128,2026-08-31T13:43:49.811979+00:00,0.12685995898209512,2.771603333996609,43,128,831.312776076798,47.52723693214773,46.18265479404875,2.771931625029538,46.17718519613052,
20260831T134334Z,ollama,qwen3.8:27b-mlx,measured,1,2,0,50050b20-0fd0-4e15-a4bb-ddfc74ada7e1,code,267,128,2026-08-31T13:43:52.584034+00:00,0.42160862497985363,2.646599249972496,54,128,159.3484419263456,56.09763282504741,48.363952344250905,2.6469858330092393,48.35688895791427,
20260831T134334Z,ollama,qwen3.8:27b-mlx,measured,1,3,0,22721212-cd1e-460f-9aa3-f2a1bb6f2f96,short,106,128,2026-08-31T13:43:55.231045+00:00,0.09599920798791572,2.2750009580049664,20,96,2500000.0,42.69653289142422,42.19778442826943,2.2753357499605045,42.19157546382611,
20260831T134334Z,ollama,qwen3.8:27b-mlx,measured,1,4,0,d95f9110-8465-4bf1-8b6d-511699a58906,medium,252,128,2026-08-31T13:43:57.506343+00:00,0.09756654204102233,2.8720681670238264,43,128,3766313.3923097136,45.01625903574264,44.56718732154595,2.8723847499932162,44.56227530114212,
1 run_id runtime model phase concurrency round slot request_id prompt_name prompt_chars max_tokens started_at ttft_s total_s prompt_tokens output_tokens prompt_tps decode_tps request_tps group_elapsed_s group_output_tps error
2 20260831T134334Z ollama qwen3.8:27b-mlx warmup 1 0 0 c3b04207-976b-4a0d-9d3c-80ef8dc4225f short 106 128 2026-08-31T13:43:39.472249+00:00 3.4916902080294676 5.4140321660088375 20 96 114.72541286980045 48.19996255746575 17.731701079044402 5.4149448340176605 17.728712469407014
3 20260831T134334Z ollama qwen3.8:27b-mlx warmup 1 1 0 47d529a2-f167-46a0-af05-a6ca0e1929a4 medium 252 128 2026-08-31T13:43:44.886979+00:00 0.35504300001775846 2.7301927499938756 43 128 157.93211765391837 52.61516193511847 46.88313673101913 2.730699084000662 46.87444352618714
4 20260831T134334Z ollama qwen3.8:27b-mlx measured 1 0 0 5b638c8b-a185-48d7-8625-f6ebacc06853 short 106 128 2026-08-31T13:43:47.617556+00:00 0.11980204097926617 2.1940376659622416 20 96 441.616869764425 45.28260592046214 43.7549461840698 2.1943347500055097 43.749022340260055
5 20260831T134334Z ollama qwen3.8:27b-mlx measured 1 1 0 fd1c62de-2412-4243-85a0-0851e2364f7c medium 252 128 2026-08-31T13:43:49.811979+00:00 0.12685995898209512 2.771603333996609 43 128 831.312776076798 47.52723693214773 46.18265479404875 2.771931625029538 46.17718519613052
6 20260831T134334Z ollama qwen3.8:27b-mlx measured 1 2 0 50050b20-0fd0-4e15-a4bb-ddfc74ada7e1 code 267 128 2026-08-31T13:43:52.584034+00:00 0.42160862497985363 2.646599249972496 54 128 159.3484419263456 56.09763282504741 48.363952344250905 2.6469858330092393 48.35688895791427
7 20260831T134334Z ollama qwen3.8:27b-mlx measured 1 3 0 22721212-cd1e-460f-9aa3-f2a1bb6f2f96 short 106 128 2026-08-31T13:43:55.231045+00:00 0.09599920798791572 2.2750009580049664 20 96 2500000.0 42.69653289142422 42.19778442826943 2.2753357499605045 42.19157546382611
8 20260831T134334Z ollama qwen3.8:27b-mlx measured 1 4 0 d95f9110-8465-4bf1-8b6d-511699a58906 medium 252 128 2026-08-31T13:43:57.506343+00:00 0.09756654204102233 2.8720681670238264 43 128 3766313.3923097136 45.01625903574264 44.56718732154595 2.8723847499932162 44.56227530114212

View File

@@ -0,0 +1,170 @@
[
{
"run_id": "20260831T134334Z",
"runtime": "ollama",
"model": "qwen3.8:27b-mlx",
"phase": "warmup",
"concurrency": 1,
"round": 0,
"slot": 0,
"request_id": "c3b04207-976b-4a0d-9d3c-80ef8dc4225f",
"prompt_name": "short",
"prompt_chars": 106,
"max_tokens": 128,
"started_at": "2026-08-31T13:43:39.472249+00:00",
"ttft_s": 3.4916902080294676,
"total_s": 5.4140321660088375,
"prompt_tokens": 20,
"output_tokens": 96,
"prompt_tps": 114.72541286980045,
"decode_tps": 48.19996255746575,
"request_tps": 17.731701079044402,
"group_elapsed_s": 5.4149448340176605,
"group_output_tps": 17.728712469407014,
"error": null
},
{
"run_id": "20260831T134334Z",
"runtime": "ollama",
"model": "qwen3.8:27b-mlx",
"phase": "warmup",
"concurrency": 1,
"round": 1,
"slot": 0,
"request_id": "47d529a2-f167-46a0-af05-a6ca0e1929a4",
"prompt_name": "medium",
"prompt_chars": 252,
"max_tokens": 128,
"started_at": "2026-08-31T13:43:44.886979+00:00",
"ttft_s": 0.35504300001775846,
"total_s": 2.7301927499938756,
"prompt_tokens": 43,
"output_tokens": 128,
"prompt_tps": 157.93211765391837,
"decode_tps": 52.61516193511847,
"request_tps": 46.88313673101913,
"group_elapsed_s": 2.730699084000662,
"group_output_tps": 46.87444352618714,
"error": null
},
{
"run_id": "20260831T134334Z",
"runtime": "ollama",
"model": "qwen3.8:27b-mlx",
"phase": "measured",
"concurrency": 1,
"round": 0,
"slot": 0,
"request_id": "5b638c8b-a185-48d7-8625-f6ebacc06853",
"prompt_name": "short",
"prompt_chars": 106,
"max_tokens": 128,
"started_at": "2026-08-31T13:43:47.617556+00:00",
"ttft_s": 0.11980204097926617,
"total_s": 2.1940376659622416,
"prompt_tokens": 20,
"output_tokens": 96,
"prompt_tps": 441.616869764425,
"decode_tps": 45.28260592046214,
"request_tps": 43.7549461840698,
"group_elapsed_s": 2.1943347500055097,
"group_output_tps": 43.749022340260055,
"error": null
},
{
"run_id": "20260831T134334Z",
"runtime": "ollama",
"model": "qwen3.8:27b-mlx",
"phase": "measured",
"concurrency": 1,
"round": 1,
"slot": 0,
"request_id": "fd1c62de-2412-4243-85a0-0851e2364f7c",
"prompt_name": "medium",
"prompt_chars": 252,
"max_tokens": 128,
"started_at": "2026-08-31T13:43:49.811979+00:00",
"ttft_s": 0.12685995898209512,
"total_s": 2.771603333996609,
"prompt_tokens": 43,
"output_tokens": 128,
"prompt_tps": 831.312776076798,
"decode_tps": 47.52723693214773,
"request_tps": 46.18265479404875,
"group_elapsed_s": 2.771931625029538,
"group_output_tps": 46.17718519613052,
"error": null
},
{
"run_id": "20260831T134334Z",
"runtime": "ollama",
"model": "qwen3.8:27b-mlx",
"phase": "measured",
"concurrency": 1,
"round": 2,
"slot": 0,
"request_id": "50050b20-0fd0-4e15-a4bb-ddfc74ada7e1",
"prompt_name": "code",
"prompt_chars": 267,
"max_tokens": 128,
"started_at": "2026-08-31T13:43:52.584034+00:00",
"ttft_s": 0.42160862497985363,
"total_s": 2.646599249972496,
"prompt_tokens": 54,
"output_tokens": 128,
"prompt_tps": 159.3484419263456,
"decode_tps": 56.09763282504741,
"request_tps": 48.363952344250905,
"group_elapsed_s": 2.6469858330092393,
"group_output_tps": 48.35688895791427,
"error": null
},
{
"run_id": "20260831T134334Z",
"runtime": "ollama",
"model": "qwen3.8:27b-mlx",
"phase": "measured",
"concurrency": 1,
"round": 3,
"slot": 0,
"request_id": "22721212-cd1e-460f-9aa3-f2a1bb6f2f96",
"prompt_name": "short",
"prompt_chars": 106,
"max_tokens": 128,
"started_at": "2026-08-31T13:43:55.231045+00:00",
"ttft_s": 0.09599920798791572,
"total_s": 2.2750009580049664,
"prompt_tokens": 20,
"output_tokens": 96,
"prompt_tps": 2500000.0,
"decode_tps": 42.69653289142422,
"request_tps": 42.19778442826943,
"group_elapsed_s": 2.2753357499605045,
"group_output_tps": 42.19157546382611,
"error": null
},
{
"run_id": "20260831T134334Z",
"runtime": "ollama",
"model": "qwen3.8:27b-mlx",
"phase": "measured",
"concurrency": 1,
"round": 4,
"slot": 0,
"request_id": "d95f9110-8465-4bf1-8b6d-511699a58906",
"prompt_name": "medium",
"prompt_chars": 252,
"max_tokens": 128,
"started_at": "2026-08-31T13:43:57.506343+00:00",
"ttft_s": 0.09756654204102233,
"total_s": 2.8720681670238264,
"prompt_tokens": 43,
"output_tokens": 128,
"prompt_tps": 3766313.3923097136,
"decode_tps": 45.01625903574264,
"request_tps": 44.56718732154595,
"group_elapsed_s": 2.8723847499932162,
"group_output_tps": 44.56227530114212,
"error": null
}
]

View File

@@ -0,0 +1,28 @@
[
{
"runtime": "ollama",
"model": "qwen3.8:27b-mlx",
"concurrency": 1,
"requests": 5,
"successes": 5,
"failures": 0,
"ttft_s_mean": 0.1723672749940306,
"ttft_s_p50": 0.11980204097926617,
"ttft_s_p95": 0.36265889178030186,
"total_s_mean": 2.551861874992028,
"total_s_p50": 2.646599249972496,
"total_s_p95": 2.8519752004183827,
"prompt_tps_mean": 1253549.1340794961,
"prompt_tps_p50": 831.312776076798,
"prompt_tps_p95": 3513050.713847771,
"decode_tps_mean": 47.324053520964824,
"decode_tps_p50": 45.28260592046214,
"decode_tps_p95": 54.383553646467476,
"request_tps_mean": 45.013305014436966,
"request_tps_p50": 44.56718732154595,
"request_tps_p95": 47.927692834210475,
"aggregate_output_tps_mean": 45.00738945185462,
"aggregate_output_tps_p50": 44.56227530114212,
"aggregate_output_tps_p95": 47.92094820555752
}
]