Back to search results
gemma-4-31B-it · IQ3_XS
NVIDIA H100 80GB HBM380GBvLLM v0.24L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-31B-it (IQ3_XS) on NVIDIA H100 80GB HBM3 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
338.72 tok/s
Decode
Decode speed
1,535.63 tok/s
Prefill
Prefill speed
0.31 s
TTFT
Time to first token
42.46 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
16 days ago
Last verified
Performance
- vLLM · IQ3_XS (current)Decode 338.72 · Prefill 1535.63 ·
- vLLM · Q3_K_M Decode 275.73 · Prefill 1508 ·
- Strata · Q5_K_S Decode 299.9 · Prefill 1290.71 ·
- Strata · Q6_K Decode 276.83 · Prefill 1508.76 ·
Core figures
- Decode (avg)
- 338.72 tok/s
- Prefill (avg)
- 1,535.63 tok/s
- TTFT (avg)
- 0.31 s
- VRAM (avg)
- 42.46 GB
- MTP acceptance rate
- —
- TTFB
- 2.71 GB
- Power draw
- 689.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-31B-it
- Quantization
- IQ3_XS
- Framework
- vLLM
- Version
- v0.24
- Context length
- 2048 tokens
- Batch size
- 16
- GPU layers
- 999
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA H100 80GB HBM3
- Nominal VRAM
- 80 GB
- Measured VRAM (avg)
- 42.46 GB
- OS
- Ubuntu 24.04
- Driver
- 572.83
- CUDA
- 12.8
- Power draw
- 689.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.24 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx
338.72 tok/s
Decode
1,535.63 tok/s
Prefill
0.31 s
TTFT
42.46 GB
VRAM
—
MTP
689.2 W
Power draw
L2 batch seed 2026-10-19: vLLM on hw_id=55 running model_id=63 at IQ3_XS