Back to search results
gemma-4-31B-it · IQ2_M
NVIDIA RTX 509032GBvLLM v0.53L2 Cross-framework verified
This page aggregates 1 real-world runs of gemma-4-31B-it (IQ2_M) on NVIDIA RTX 5090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
219.67 tok/s
Decode
Decode speed
1,152.52 tok/s
Prefill
Prefill speed
2.12 s
TTFT
Time to first token
30.4 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · IQ2_M (current)Decode 219.67 · Prefill 1152.52 ·
- llama.cpp · IQ2_M Decode 159.29 · Prefill 615.31 ·
- Ollama · IQ1_S Decode 146.23 · Prefill 719.62 ·
- vLLM · IQ2_XS Decode 145.1 · Prefill 1088.3 ·
- vLLM · Q5_K_M Decode 66.2 · Prefill 496.5 ·
- vLLM · Q4_K_M Decode 81 · Prefill 607.5 ·
- llama.cpp · IQ2_XS Decode 133.1 · Prefill 998.3 ·
- llama.cpp · Q5_K_M Decode 60.8 · Prefill 456 ·
- llama.cpp · Q4_K_M Decode 74.3 · Prefill 557.3 ·
Core figures
- Decode (avg)
- 219.67 tok/s
- Prefill (avg)
- 1,152.52 tok/s
- TTFT (avg)
- 2.12 s
- VRAM (avg)
- 30.4 GB
- MTP acceptance rate
- —
- TTFB
- 1.76 GB
- Power draw
- 476.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-31B-it
- Quantization
- IQ2_M
- Framework
- vLLM
- Version
- v0.53
- Context length
- 8192 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 RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 30.4 GB
- OS
- Ubuntu 22.04
- Driver
- 572.83
- CUDA
- 12.4
- Power draw
- 476.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.53 · Ubuntu 22.04 · CUDA 12.4 · 8192 ctx
219.67 tok/s
Decode
1,152.52 tok/s
Prefill
2.12 s
TTFT
30.4 GB
VRAM
—
MTP
476.5 W
Power draw
L2 batch seed 2026-10-18: vLLM on hw_id=13 running model_id=63 at IQ2_M