Back to search results
gemma-4-26B-A4B-it · IQ2_XS
NVIDIA RTX 509032GBvLLM 0.7.3L0 Self-reported
This page aggregates 1 real-world runs of gemma-4-26B-A4B-it (IQ2_XS) on NVIDIA RTX 5090 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
173.1 tok/s
Decode
Decode speed
1,298.3 tok/s
Prefill
Prefill speed
0.08 s
TTFT
Time to first token
9.3 GB
VRAM
VRAM usage
L0 Self-reported
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- vLLM · IQ2_XS (current)Decode 173.1 · Prefill 1298.3 ·
- vLLM · Q5_K_M Decode 78.9 · Prefill 591.8 ·
- vLLM · Q4_K_M Decode 96.4 · Prefill 723 ·
- llama.cpp · IQ2_XS Decode 158.8 · Prefill 1191 ·
- llama.cpp · Q5_K_M Decode 72.4 · Prefill 543 ·
- llama.cpp · Q4_K_M Decode 88.5 · Prefill 663.8 ·
Core figures
- Decode (avg)
- 173.1 tok/s
- Prefill (avg)
- 1,298.3 tok/s
- TTFT (avg)
- 0.08 s
- VRAM (avg)
- 9.3 GB
- MTP acceptance rate
- —
- TTFB
- — GB
- Power draw
- — W
Configuration
Member-level fields are taken from the most recent run
- Model
- gemma-4-26B-A4B-it
- Quantization
- IQ2_XS
- Framework
- vLLM
- Version
- 0.7.3
- Context length
- 4096 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 RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 9.3 GB
- OS
- Linux
- Driver
- 570.65
- CUDA
- 12.6
Sources & evidence
1 measured records in total, each traceable to its original source
0.7.3 · Linux · CUDA 12.6 · 4096 ctx
173.1 tok/s
Decode
1,298.3 tok/s
Prefill
0.08 s
TTFT
9.3 GB
VRAM
—
MTP
— W
Power draw
L0 理论估算（add-1000-records-batch3）