Back to search results
gemma-4-31B-it · Q8_0
NVIDIA H2097GBOllama v0.33L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-31B-it (Q8_0) on NVIDIA H20 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
18.96 tok/s
Decode
Decode speed
65.76 tok/s
Prefill
Prefill speed
1.01 s
TTFT
Time to first token
76.97 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 Decode 39.95 · Prefill 179.27 ·
- vLLM · Q4_K_S Decode 32.57 · Prefill 141.17 ·
- Ollama · Q8_0 (current)Decode 18.96 · Prefill 65.76 ·
Core figures
- Decode (avg)
- 18.96 tok/s
- Prefill (avg)
- 65.76 tok/s
- TTFT (avg)
- 1.01 s
- VRAM (avg)
- 76.97 GB
- MTP acceptance rate
- —
- TTFB
- 0.15 GB
- Power draw
- 339.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-31B-it
- Quantization
- Q8_0
- Framework
- Ollama
- Version
- v0.33
- Context length
- 8192 tokens
- Batch size
- 512
- GPU layers
- 99
- Flash Attention
- On
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)
- 76.97 GB
- OS
- Ubuntu 22.04
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 339.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.33 · Ubuntu 22.04 · CUDA 12.8 · 8192 ctx
18.96 tok/s
Decode
65.76 tok/s
Prefill
1.01 s
TTFT
76.97 GB
VRAM
—
MTP
339.5 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=56 running model_id=63 at Q8_0