Back to search results
Qwen3.8-9B · Q3_K_M
NVIDIA H2097GBStrata v0.25L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_M) on NVIDIA H20 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
74.4 tok/s
Decode
Decode speed
349.95 tok/s
Prefill
Prefill speed
1.65 s
TTFT
Time to first token
14.95 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- vLLM · IQ3_S Decode 57.73 · Prefill 250.91 ·
- vLLM · Q3_K_L Decode 54.56 · Prefill 274.28 ·
- Strata · IQ3_S Decode 80.72 · Prefill 287.96 ·
- Strata · Q3_K_M (current)Decode 74.4 · Prefill 349.95 ·
Core figures
- Decode (avg)
- 74.4 tok/s
- Prefill (avg)
- 349.95 tok/s
- TTFT (avg)
- 1.65 s
- VRAM (avg)
- 14.95 GB
- MTP acceptance rate
- 0.71
- TTFB
- 0.6 GB
- Power draw
- 334.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q3_K_M
- Framework
- Strata
- Version
- v0.25
- Context length
- 16384 tokens
- Batch size
- 1024
- GPU layers
- 5
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA H20
- Nominal VRAM
- 97 GB
- Measured VRAM (avg)
- 14.95 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 334.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.25 · Windows 11 23H2 · CUDA 12.8 · 16384 ctx
74.4 tok/s
Decode
349.95 tok/s
Prefill
1.65 s
TTFT
14.95 GB
VRAM
0.71
MTP
334.6 W
Power draw
L2 batch seed 2026-10-19: Strata on hw_id=56 running model_id=52 at Q3_K_M