Back to search results
Qwen3-8B · Q3_K_L
NVIDIA RTX 508016GBOllama v0.53L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q3_K_L) on NVIDIA RTX 5080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
101.88 tok/s
Decode
Decode speed
405.42 tok/s
Prefill
Prefill speed
0.62 s
TTFT
Time to first token
14.2 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · Q5_K_S Decode 91.75 · Prefill 454.66 ·
- Ollama · Q3_K_L (current)Decode 101.88 · Prefill 405.42 ·
- Strata · IQ4_XS Decode 144.31 · Prefill 545.08 ·
Core figures
- Decode (avg)
- 101.88 tok/s
- Prefill (avg)
- 405.42 tok/s
- TTFT (avg)
- 0.62 s
- VRAM (avg)
- 14.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.82 GB
- Power draw
- 301.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q3_K_L
- Framework
- Ollama
- Version
- v0.53
- Context length
- 8192 tokens
- Batch size
- 512
- GPU layers
- 20
- 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)
- 14.2 GB
- OS
- Ubuntu 24.04
- Driver
- 555.85
- CUDA
- 12.6
- Power draw
- 301.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.53 · Ubuntu 24.04 · CUDA 12.6 · 8192 ctx
101.88 tok/s
Decode
405.42 tok/s
Prefill
0.62 s
TTFT
14.2 GB
VRAM
—
MTP
301.4 W
Power draw
L2 batch seed 2026-10-10: Ollama on hw_id=14 running model_id=53 at Q3_K_L