Speed test matrix

GLM-5.3 on H200 SXM 141GB ×8

vllm · 0.29.0 · FP86 contexts (8K–251K) × 8 concurrency levels (1–128) · prefill at 8K, 16K, 32K, 64K, 128K, 251K, 256K

by @keennaylmx dev importMeasured Sep 15, 2026, 01:05 UTC

Hardware

Type: Discrete GPU
GPU: H200 SXM
GPU count: 8
VRAM: 1128 GB (8 × 141 GB)
OS: linux

Engine

Engine: vllm
Version: 0.29.0
Quantization: FP8
Backend: cuda
Repository: github.com/vllm-project/vllm
Build: cuda-13.2

Run

Served model: glm
Revision: main
Benchmark tool: llm-inference-bench v0.6.2
Decode test: Fixed duration
Prefill mode: Measured during decode warm-up
Time per measurement: 30 s
Max output: 4,096 tokens

Launch command

"$HOME/env_h200-glm53-vllm-v0290/bin/vllm" serve zai-org/GLM-5.3 --served-model-name glm --tensor-parallel-size 8 --reasoning-parser glm45 --enable-auto-tool-choice --tool-call-parser glm47 --max-model-len 262144 --gpu-memory-utilization 0.88 --host 0.0.0.0 --port 8000 --api-key <redacted> --dtype bfloat16 --kv-cache-dtype bfloat16 --no-enable-flashinfer-autotune --speculative-config '{"method":"dflash","model":"incoai/GLM-5.3-DFlash2","num_speculative_tokens":7}'

Prefill

prompt tok/s by context length

8K context11.9K689 ms TTFT

16K context11.8K1,376 ms TTFT

32K context11.3K2,853 ms TTFT

64K context10.7K6,045 ms TTFT

128K context9,60213,423 ms TTFT

251K context7,89332,001 ms TTFT

256K context7,88732,666 ms TTFT

Sustained decode

total tok/s · rows are context length, columns are simultaneous requests

Context	1	2	4	8	16	32	64	128
8K	170.263 ms TTFT	295.689 ms TTFT	394.9144 ms TTFT	661.9167 ms TTFT	1,056.5310 ms TTFT	Over capacity	Over capacity	Over capacity
16K	155.184 ms TTFT	283.0104 ms TTFT	392.7166 ms TTFT	661.6235 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity
32K	161.4113 ms TTFT	282.9131 ms TTFT	405.1206 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity
64K	162.1190 ms TTFT	285.0197 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity
128K	173.0376 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity
251K	150.5800 ms TTFT	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity	Over capacity

Over capacity: not run because this many requests at this context would exceed the server's KV cache.

TTFT is measured after the benchmark warms the server's prompt cache, so it mostly excludes prefill.

All measurements

Latencies are medians. Total tok/s is output across all simultaneous requests.

Phase	Context	Requests at once	Status	Total tok/s	Per request tok/s	TTFT	Time between tokens	Average active requests	Completed requests	Output tokens	Measured for
Prefill	8K	1	Valid	11.9K	—	689 ms	—	—	1	—	—
Prefill	16K	1	Valid	11.8K	—	1,376 ms	—	—	1	—	—
Prefill	32K	1	Valid	11.3K	—	2,853 ms	—	—	1	—	—
Prefill	64K	1	Valid	10.7K	—	6,045 ms	—	—	1	—	—
Prefill	128K	1	Valid	9,602.0	—	13,423 ms	—	—	1	—	—
Prefill	251K	1	Valid	7,893.0	—	32,001 ms	—	—	1	—	—
Prefill	256K	1	Valid	7,887.0	—	32,666 ms	—	—	1	—	—
Sustained decode	8K	1	Valid	170.2	175.3	63 ms	5.7 ms	1.0	1	5,104	30.0 s
Sustained decode	8K	2	Valid	295.6	155.4	89 ms	6.4 ms	2.0	2	8,868	30.0 s
Sustained decode	8K	4	Valid	394.9	102.3	144 ms	9.8 ms	4.0	0	11,846	30.0 s
Sustained decode	8K	8	Valid	661.9	83.7	167 ms	11.9 ms	8.0	0	19,839	30.0 s
Sustained decode	8K	16	Valid	1,056.5	68.1	310 ms	14.7 ms	16.0	0	31,685	30.0 s
Sustained decode	8K	32	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	8K	64	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	8K	128	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	16K	1	Valid	155.1	161.9	84 ms	6.2 ms	1.0	1	4,651	30.0 s
Sustained decode	16K	2	Valid	283.0	149.4	104 ms	6.7 ms	2.0	2	8,488	30.0 s
Sustained decode	16K	4	Valid	392.7	100.4	166 ms	10.0 ms	4.0	0	11,776	30.0 s
Sustained decode	16K	8	Valid	661.6	85.7	235 ms	11.7 ms	8.0	0	19,837	30.0 s
Sustained decode	16K	16	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	16K	32	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	16K	64	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	16K	128	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	32K	1	Valid	161.4	179.1	113 ms	5.7 ms	1.0	1	4,842	30.0 s
Sustained decode	32K	2	Valid	282.9	147.9	131 ms	6.8 ms	2.0	2	8,485	30.0 s
Sustained decode	32K	4	Valid	405.1	105.4	206 ms	9.5 ms	4.0	0	12,148	30.0 s
Sustained decode	32K	8	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	32K	16	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	32K	32	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	32K	64	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	32K	128	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	64K	1	Valid	162.1	169.1	190 ms	5.9 ms	1.0	1	4,862	30.0 s
Sustained decode	64K	2	Valid	285.0	146.3	197 ms	6.8 ms	2.0	2	8,551	30.0 s
Sustained decode	64K	4	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	64K	8	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	64K	16	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	64K	32	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	64K	64	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	64K	128	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	128K	1	Valid	173.0	178.5	376 ms	5.6 ms	1.0	1	5,191	30.0 s
Sustained decode	128K	2	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	128K	4	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	128K	8	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	128K	16	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	128K	32	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	128K	64	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	128K	128	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	251K	1	Valid	150.5	165.7	800 ms	6.1 ms	1.0	1	4,513	30.0 s
Sustained decode	251K	2	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	251K	4	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	251K	8	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	251K	16	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	251K	32	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	251K	64	Over capacity	—	—	—	—	—	—	—	—
Sustained decode	251K	128	Over capacity	—	—	—	—	—	—	—	—

Over capacity: not run because this many requests at this context would exceed the server's KV cache.