Back to search results
Qwen3.5-4B · IQ3_XS
NVIDIA RTX 407012GBStrata v0.34L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (IQ3_XS) on NVIDIA RTX 4070 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
180.02 tok/s
Decode
Decode speed
970.61 tok/s
Prefill
Prefill speed
1.54 s
TTFT
Time to first token
7.31 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Strata · IQ3_XS (current)Decode 180.02 · Prefill 970.61 ·
Core figures
- Decode (avg)
- 180.02 tok/s
- Prefill (avg)
- 970.61 tok/s
- TTFT (avg)
- 1.54 s
- VRAM (avg)
- 7.31 GB
- MTP acceptance rate
- 0.52
- TTFB
- 1.44 GB
- Power draw
- 225 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- IQ3_XS
- Framework
- Strata
- Version
- v0.34
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 8
- 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
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 7.31 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.6
- Power draw
- 225 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.34 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx
180.02 tok/s
Decode
970.61 tok/s
Prefill
1.54 s
TTFT
7.31 GB
VRAM
0.52
MTP
225 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=45 running model_id=48 at IQ3_XS