Pulse report — Lenovo Yoga Pro 9 16IMH9¶

Submitted 2026-05-15T14:47:48+00:00 · fingerprint 82ca8fd996230de1

Summary¶

28 ok · 1 skipped · 0 failed

benchmark	status	duration	summary
`cpu_python`	ok	0.28s	sieve 101.85 Mops/s, arith 18.81 Mops/s
`cpu_hash`	ok	4.00s	SHA-256 single-thread (16 MiB chunks): 2227 MiB/s
`cpu_compress`	ok	7.57s	zlib c/d 55/354 MiB/s, lzma 5 MiB/s, zlib ratio 0.66
`sqlite_oltp`	ok	8.02s	WAL mode: inserts=58265 selects=5346 updates=41551 ops/s
`memory`	ok	2.08s	memcpy 16883 MiB/s (ctypes), 1MiB alloc 61112/s
`disk_seq`	ok	0.38s	seq write 997 MiB/s, seq read 2156 MiB/s (256 MiB, O_DIRECT)
`disk_rand`	ok	3.87s	random 4K read: 5167 IOPS (O_DIRECT)
`network_download`	ok	11.62s	max 2.7 MiB/s (23 Mbps), median 2.5 MiB/s, σ=0.3 (3 samples)
`llm_inference`	ok	5.34s	tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf on llama-cpp-python (22 threads): pp512=283.6 tok/s · tg128=40.9 tok/s
`gpu_compute`	ok	1.03s	NVIDIA CUDA / NVIDIA GeForce RTX 4070 Laptop GPU (pyopencl-naive): 166.7 GFLOPS @ 2048^3
`sysbench_cpu`	ok	30.01s	sysbench cpu @ 22t, prime=20000: 22602 events/s
`sysbench_memory`	ok	0.08s	sysbench memory read: 54579 MiB/s
`sysbench_threads`	ok	20.01s	sysbench threads @ 16t: 12664 events/s
`stream`	ok	0.82s	STREAM Triad 62.7 GB/s (Copy 79.3 · Scale 60.4 · Add 65.1) · 1144 MiB working set
`fio_disk`	ok	62.43s	4K randread 202506 IOPS · 1M seqwrite 841 MiB/s
`stress_ng_cpu`	ok	30.04s	stress-ng cpu @ 22t (matrixprod): 29597 bogo-ops/s
`stress_ng_memory`	ok	30.03s	stress-ng memrate: 2 bogo-ops/s
`7zip`	ok	30.24s	compress 100 MIPS, decompress 4415 MIPS
`openssl_speed`	ok	18.00s	AES-256-GCM (16K blocks): 7437 MiB/s
`c_ray`	ok	8.86s	c-ray-mt 7680x4320 rays=16 threads=22: 7.82 s
`ffmpeg_x264_encode`	ok	3.54s	x264 encode 900 frames @ 1080p in 3.5s = 254.0 fps (last reported: 258.0 fps)
`blender_bmw27`	ok	118.18s	BMW27 (CYCLES, 100% resolution): 117.4 s (wall: 118.2 s)
`glmark2`	ok	124.90s	glmark2 score: 1849
`docker`	skipped	0.05s	/usr/bin/docker info failed (daemon not running or no permission): failed to connect to the docker API at unix:///var/ru
`compile_sqlite`	ok	14.62s	sqlite3.c compiled in 14.62s (17499 lines/s) using cc
`compile_cpp`	ok	1.44s	json.hpp compiled in 1.44s (17244 header lines/s) using c++
`compile_java`	ok	10.70s	javac compiled 500 classes / 786000 LOC in 10.70s (73474 lines/s)
`compile_redis`	ok	7.90s	redis built in 7.9s with -j8 (151 object files)
`browser_js`	ok	12.40s	headless JS: 100.0 ops/s (median 10.00±3.27 ms, 1215 runs)

Subscores¶

Geomean of the per-bench headline metric within each category, normalised against the reference baseline (100 = parity).

category	score
compress	0.1
cpu	50.0
crypto	93.0
disk	17.4
gpu	1.4
media	127.0
memory	207.9
ml	51.1
render	72.3

System¶

field	value
platform	`linux/ubuntu/x86_64`
CPU	Intel(R) Core(TM) Ultra 9 185H (22 threads)
RAM	62.4 GiB
motherboard	LENOVO LNVNB161216
governor	`powersave`
NUMA	1 node(s)
GPU	nvidia: NVIDIA GeForce RTX 4070 Laptop GPU (8188 MiB, drv 590.48.01)
Submitter	Patrik Maly maly.patrik007@gmail.com

Detail¶

`cpu_python` — cpu¶

status: ok · duration: 0.28s

sieve 101.85 Mops/s, arith 18.81 Mops/s

metric	value	unit
sieve_throughput	101.9	Mops/s
arith_throughput	18.81	Mops/s
primes_found	1.489e+05	primes

`cpu_hash` — cpu¶

status: ok · duration: 4.00s

SHA-256 single-thread (16 MiB chunks): 2227 MiB/s

metric	value	unit
sha256_throughput	2227	MiB/s
chunk_size_mib	16	MiB

`cpu_compress` — cpu¶

status: ok · duration: 7.57s

zlib c/d 55/354 MiB/s, lzma 5 MiB/s, zlib ratio 0.66

metric	value	unit
zlib_compress	55.49	MiB/s
zlib_decompress	353.9	MiB/s
lzma_compress	4.636	MiB/s
zlib_ratio	0.665	ratio

`sqlite_oltp` — database¶

status: ok · duration: 8.02s

WAL mode: inserts=58265 selects=5346 updates=41551 ops/s

metric	value	unit
inserts_per_s	5.827e+04	ops/s
selects_per_s	5346	ops/s
updates_per_s	4.155e+04	ops/s
txn_per_s	1.052e+05	ops/s

`memory` — memory¶

status: ok · duration: 2.08s

memcpy 16883 MiB/s (ctypes), 1MiB alloc 61112/s

metric	value	unit
memcpy	1.688e+04	MiB/s
alloc_1mib_per_sec	6.111e+04	allocs/s

`disk_seq` — disk¶

status: ok · duration: 0.38s

seq write 997 MiB/s, seq read 2156 MiB/s (256 MiB, O_DIRECT)

metric	value	unit
seq_write	996.7	MiB/s
seq_read	2156	MiB/s
file_size_mib	256	MiB

`disk_rand` — disk¶

status: ok · duration: 3.87s

random 4K read: 5167 IOPS (O_DIRECT)

metric	value	unit
rand_read_iops	5167	IOPS
rand_read_throughput	20.18	MiB/s
file_size_mib	512	MiB

`network_download` — network¶

status: ok · duration: 11.62s

max 2.7 MiB/s (23 Mbps), median 2.5 MiB/s, σ=0.3 (3 samples)

metric	value	unit
download_max_mibps	2.733	MiB/s
download_median_mibps	2.531	MiB/s
download_max_mbps	22.93	Mbps
download_median_mbps	21.23	Mbps
download_stdev_mibps	0.2758	MiB/s
download_samples	3	n

`llm_inference` — ml¶

status: ok · duration: 5.34s

tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf on llama-cpp-python (22 threads): pp512=283.6 tok/s · tg128=40.9 tok/s

metric	value	unit
llm_pp512_tokens_per_sec	283.6	tok/s
llm_tg128_tokens_per_sec	40.87	tok/s

`gpu_compute` — gpu¶

status: ok · duration: 1.03s

NVIDIA CUDA / NVIDIA GeForce RTX 4070 Laptop GPU (pyopencl-naive): 166.7 GFLOPS @ 2048^3

metric	value	unit
gpu_sgemm_gflops	166.7	GFLOPS
gpu_matmul_size	2048	N

`sysbench_cpu` — cpu¶

status: ok · duration: 30.01s

sysbench cpu @ 22t, prime=20000: 22602 events/s

metric	value	unit
sysbench_cpu_events_per_sec	2.26e+04	events/s
sysbench_cpu_threads	22	threads

`sysbench_memory` — memory¶

status: ok · duration: 0.08s

sysbench memory read: 54579 MiB/s

metric	value	unit
sysbench_memory_read	5.458e+04	MiB/s

`sysbench_threads` — cpu¶

status: ok · duration: 20.01s

sysbench threads @ 16t: 12664 events/s

metric	value	unit
sysbench_threads_events_per_sec	1.266e+04	events/s
sysbench_threads_count	16	threads

`stream` — memory¶

status: ok · duration: 0.82s

STREAM Triad 62.7 GB/s (Copy 79.3 · Scale 60.4 · Add 65.1) · 1144 MiB working set

metric	value	unit
stream_copy_gb_s	79.35	GB/s
stream_scale_gb_s	60.41	GB/s
stream_add_gb_s	65.07	GB/s
stream_triad_gb_s	62.68	GB/s

`fio_disk` — disk¶

status: ok · duration: 62.43s

4K randread 202506 IOPS · 1M seqwrite 841 MiB/s

metric	value	unit
fio_randread_iops	2.025e+05	IOPS
fio_randread_throughput	791	MiB/s
fio_seqwrite_throughput	840.9	MiB/s

`stress_ng_cpu` — cpu¶

status: ok · duration: 30.04s

stress-ng cpu @ 22t (matrixprod): 29597 bogo-ops/s

metric	value	unit
stress_ng_cpu_bogo_ops_per_sec	2.96e+04	bogo-ops/s
stress_ng_cpu_threads	22	threads

`stress_ng_memory` — memory¶

status: ok · duration: 30.03s

stress-ng memrate: 2 bogo-ops/s

metric	value	unit
stress_ng_memrate_bogo_ops_per_sec	2.07	bogo-ops/s

`7zip` — compress¶

status: ok · duration: 30.24s

compress 100 MIPS, decompress 4415 MIPS

metric	value	unit
7z_compress_rating	100	MIPS
7z_decompress_rating	4415	MIPS

`openssl_speed` — crypto¶

status: ok · duration: 18.00s

AES-256-GCM (16K blocks): 7437 MiB/s

metric	value	unit
aes256_gcm	7437	MiB/s

`c_ray` — render¶

status: ok · duration: 8.86s

c-ray-mt 7680x4320 rays=16 threads=22: 7.82 s

metric	value	unit
c_ray_render_time_s	7.823	s
c_ray_threads	22	threads

`ffmpeg_x264_encode` — media¶

status: ok · duration: 3.54s

x264 encode 900 frames @ 1080p in 3.5s = 254.0 fps (last reported: 258.0 fps)

metric	value	unit
ffmpeg_x264_encode_fps	254	fps
ffmpeg_x264_output_mib	22.9	MiB

`blender_bmw27` — render¶

status: ok · duration: 118.18s

BMW27 (CYCLES, 100% resolution): 117.4 s (wall: 118.2 s)

metric	value	unit
blender_bmw27_render_seconds	117.4	s

`glmark2` — gpu¶

status: ok · duration: 124.90s

glmark2 score: 1849

metric	value	unit
glmark2_score	1849	points

`docker` — container¶

status: skipped · duration: 0.05s

skipped: /usr/bin/docker info failed (daemon not running or no permission): failed to connect to the docker API at unix:///var/run/docker.sock; check if the path is correct and if the daemon is running: dial unix /var/run/docker.sock: connect: no such file or directory

`compile_sqlite` — compile¶

status: ok · duration: 14.62s

sqlite3.c compiled in 14.62s (17499 lines/s) using cc

metric	value	unit
compile_time	14.62	s
compile_throughput	1.75e+04	lines/s
download_time	3.301	s

`compile_cpp` — compile¶

status: ok · duration: 1.44s

json.hpp compiled in 1.44s (17244 header lines/s) using c++

metric	value	unit
cpp_compile_time	1.436	s
cpp_compile_throughput	1.724e+04	lines/s
download_time	0.6114	s

`compile_java` — compile¶

status: ok · duration: 10.70s

javac compiled 500 classes / 786000 LOC in 10.70s (73474 lines/s)

metric	value	unit
javac_time	10.7	s
javac_lines_per_sec	7.347e+04	lines/s
javac_classes_per_sec	46.74	classes/s

`compile_redis` — compile¶

status: ok · duration: 7.90s

redis built in 7.9s with -j8 (151 object files)

metric	value	unit
redis_build_time	7.899	s
redis_objs_per_sec	19.12	objs/s
redis_jobs	8	threads
download_time	1.331	s

`browser_js` — browser¶

status: ok · duration: 12.40s

headless JS: 100.0 ops/s (median 10.00±3.27 ms, 1215 runs)

metric	value	unit
js_ops_per_sec	100	ops/s
js_median_ms	10	ms
js_min_ms	5.1	ms
js_stdev_ms	3.27	ms
js_runs	1215	runs

Pulse report — Lenovo Yoga Pro 9 16IMH9¶

Summary¶

Subscores¶

System¶

Detail¶

cpu_python — cpu¶

cpu_hash — cpu¶

cpu_compress — cpu¶

sqlite_oltp — database¶

memory — memory¶

disk_seq — disk¶

disk_rand — disk¶

network_download — network¶

llm_inference — ml¶

gpu_compute — gpu¶

sysbench_cpu — cpu¶

sysbench_memory — memory¶

sysbench_threads — cpu¶

stream — memory¶

fio_disk — disk¶

stress_ng_cpu — cpu¶

stress_ng_memory — memory¶

7zip — compress¶

openssl_speed — crypto¶

c_ray — render¶

ffmpeg_x264_encode — media¶

blender_bmw27 — render¶

glmark2 — gpu¶

docker — container¶

compile_sqlite — compile¶

compile_cpp — compile¶

compile_java — compile¶

compile_redis — compile¶

browser_js — browser¶