Back to search results
Qwen3-8B · IQ1_S
NVIDIA RTX 508016GBStrata v0.23L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (IQ1_S) on NVIDIA RTX 5080 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
376.58 tok/s
Decode
Decode speed
1,681.2 tok/s
Prefill
Prefill speed
1.08 s
TTFT
Time to first token
9.16 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- Ollama · Q5_K_S Decode 128.2 · Prefill 585.03 ·
- Strata · IQ1_S (current)Decode 376.58 · Prefill 1681.2 ·
- llama.cpp · Q5_K_S Decode 91.75 · Prefill 454.66 ·
- Ollama · Q3_K_L Decode 101.88 · Prefill 405.42 ·
- Strata · IQ4_XS Decode 144.31 · Prefill 545.08 ·
Core figures
- Decode (avg)
- 376.58 tok/s
- Prefill (avg)
- 1,681.2 tok/s
- TTFT (avg)
- 1.08 s
- VRAM (avg)
- 9.16 GB
- MTP acceptance rate
- 0.51
- TTFB
- 3.01 GB
- Power draw
- 293.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- IQ1_S
- Framework
- Strata
- Version
- v0.23
- Context length
- 8192 tokens
- Batch size
- 256
- 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 5080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 9.16 GB
- OS
- Ubuntu 22.04
- Driver
- 565.57
- CUDA
- 12.8
- Power draw
- 293.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.23 · Ubuntu 22.04 · CUDA 12.8 · 8192 ctx
376.58 tok/s
Decode
1,681.2 tok/s
Prefill
1.08 s
TTFT
9.16 GB
VRAM
0.51
MTP
293.4 W
Power draw
L2 batch seed 2026-10-18: Strata on hw_id=14 running model_id=53 at IQ1_S