Qwen3.8-27B W4A16-AWQ on H200
safetensors INT4_G128_ZP+BF16
Engines
vLLM
0.31.0 ↗measured 2026-11-09 23:02 UTC
100.8 tok/s
34% of the roofline299.1 tok/s possible
- now, a token
- 9.92 ms
- floor
- 3.34 ms
- read, a token
- 15.59 GB
Speed at context
128 tokens
512 tokens
Where the time goes
- Now, a token
- 9.92 ms
- Roofline floor, a token
- 3.34 ms
- Gap to the floor
- 6.57 ms
- Kernels a token
- 840
Per role ms a token. floor (bytes ÷ measured memory speed) above the floor
Per kernel (33): ms now / ms at the roofline, launches a token
No floor = the kernel reads no weights (norms, conversions, copies): all of its time is gap.
Run h200-qwen3.8-27b-awq-vllm-k8
Tested on
- GPU
- H200 · 140 GB
- System RAM
- 1511 GB
- CPU threads
- 256
- Memory, measured
- 4662 GB/s
- Temp, max
- see notes
- Power
- see notes
- SM clock
- –
- Driver
- 595.91.07
- Measured
- 2026-11-09 23:02 UTC · context 512 tokens · measured, in-model (nsys): split by role from the engine's own labels, 9 weight roles
Qwen3.8-27B on other GPUs
RTX 5090vLLM + MTP, 4-bit draft layer · W4A16-AWQ · 4-bit head202.1 tok/s H200vLLM · W4A16-AWQ100.8 tok/s · 34%2× Radeon R9700vLLM + MTP k=2 · Quark W4A1692.3 tok/s H100 80GBvLLM · W4A16-AWQ87.8 tok/s · 41%H200 NVLllama.cpp · UD-Q4_K_M78.6 tok/s · 27%2× RTX 3090vLLM · W4A16-AWQ68.6 tok/s · 76%RTX 4090vLLM · W4A16-AWQ54.4 tok/s · 88%RTX 3090vLLM · W4A16-AWQ46.2 tok/s · 80%L40SvLLM · W4A16-AWQ43.6 tok/s · 89%
The fastest setup measured on each GPU, one user. The percentage is that GPU's own roofline.