Back to search results
Qwen3-8B · Q5_K_S
NVIDIA RTX 309024GBStrata v0.21L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q5_K_S) on NVIDIA RTX 3090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
138.04 tok/s
Decode
Decode speed
495.5 tok/s
Prefill
Prefill speed
0.9 s
TTFT
Time to first token
17.22 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- Ollama · IQ4_XS Decode 114.83 · Prefill 486.18 ·
- Strata · Q5_K_S (current)Decode 138.04 · Prefill 495.5 ·
- llama.cpp · Q8_0 Decode 84.9 · Prefill 636.8 ·
- llama.cpp · Q5_K_M Decode 123.7 · Prefill 927.8 ·
- llama.cpp · Q4_K_M Decode 149 · Prefill 1117.5 ·
Core figures
- Decode (avg)
- 138.04 tok/s
- Prefill (avg)
- 495.5 tok/s
- TTFT (avg)
- 0.9 s
- VRAM (avg)
- 17.22 GB
- MTP acceptance rate
- 0.63
- TTFB
- 1.1 GB
- Power draw
- 323.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q5_K_S
- Framework
- Strata
- Version
- v0.21
- Context length
- 16384 tokens
- Batch size
- 1024
- GPU layers
- 15
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 17.22 GB
- OS
- Windows 11 23H2
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 323.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.21 · Windows 11 23H2 · CUDA 12.8 · 16384 ctx
138.04 tok/s
Decode
495.5 tok/s
Prefill
0.9 s
TTFT
17.22 GB
VRAM
0.63
MTP
323.4 W
Power draw
L2 batch seed 2026-10-10: Strata on hw_id=2 running model_id=53 at Q5_K_S