Back to search results
Qwen3.5-9B · IQ2_XS
NVIDIA RTX 4070 Ti12GBvLLM v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (IQ2_XS) on NVIDIA RTX 4070 Ti with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
105.73 tok/s
Decode
Decode speed
467.89 tok/s
Prefill
Prefill speed
0.89 s
TTFT
Time to first token
11.17 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · IQ2_XS (current)Decode 105.73 · Prefill 467.89 ·
Core figures
- Decode (avg)
- 105.73 tok/s
- Prefill (avg)
- 467.89 tok/s
- TTFT (avg)
- 0.89 s
- VRAM (avg)
- 11.17 GB
- MTP acceptance rate
- —
- TTFB
- 0.85 GB
- Power draw
- 263.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- IQ2_XS
- Framework
- vLLM
- Version
- v0.26
- 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 RTX 4070 Ti
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 11.17 GB
- OS
- Windows 11 23H2
- Driver
- 555.85
- CUDA
- 12.6
- Power draw
- 263.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx
105.73 tok/s
Decode
467.89 tok/s
Prefill
0.89 s
TTFT
11.17 GB
VRAM
—
MTP
263.6 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=42 running model_id=49 at IQ2_XS