Back to search results
Qwen3.5-4B · Q4_K_S
NVIDIA RTX 509032GBStrata v0.30L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-4B (Q4_K_S) on NVIDIA RTX 5090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
353.67 tok/s
Decode
Decode speed
1,676.75 tok/s
Prefill
Prefill speed
2.44 s
TTFT
Time to first token
8.65 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · Q3_K_L Decode 338.21 · Prefill 1409.78 ·
- vLLM · Q3_K_M Decode 356.1 · Prefill 1633.97 ·
- vLLM · Q3_K_S Decode 324.89 · Prefill 1253.12 ·
- Strata · Q4_K_S (current)Decode 353.67 · Prefill 1676.75 ·
Core figures
- Decode (avg)
- 353.67 tok/s
- Prefill (avg)
- 1,676.75 tok/s
- TTFT (avg)
- 2.44 s
- VRAM (avg)
- 8.65 GB
- MTP acceptance rate
- 0.64
- TTFB
- 2.83 GB
- Power draw
- 591.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-4B
- Quantization
- Q4_K_S
- Framework
- Strata
- Version
- v0.30
- Context length
- 2048 tokens
- Batch size
- 512
- GPU layers
- 12
- 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)
- 8.65 GB
- OS
- Ubuntu 22.04
- Driver
- 560.94
- CUDA
- 12.4
- Power draw
- 591.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.30 · Ubuntu 22.04 · CUDA 12.4 · 2048 ctx
353.67 tok/s
Decode
1,676.75 tok/s
Prefill
2.44 s
TTFT
8.65 GB
VRAM
0.64
MTP
591.1 W
Power draw
L2 batch seed 2026-10-10: Strata on hw_id=13 running model_id=48 at Q4_K_S