Back to search results
Qwen3-8B · Q6_K
NVIDIA H100 80GB HBM380GBOllama v0.46L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q6_K) on NVIDIA H100 80GB HBM3 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
301.71 tok/s
Decode
Decode speed
1,324.79 tok/s
Prefill
Prefill speed
1 s
TTFT
Time to first token
18.9 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
17 days ago
Last verified
Performance
- vLLM · IQ1_S Decode 335.51 · Prefill 1078.48 ·
- Ollama · Q6_K (current)Decode 301.71 · Prefill 1324.79 ·
Core figures
- Decode (avg)
- 301.71 tok/s
- Prefill (avg)
- 1,324.79 tok/s
- TTFT (avg)
- 1 s
- VRAM (avg)
- 18.9 GB
- MTP acceptance rate
- —
- TTFB
- 2.41 GB
- Power draw
- 583 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q6_K
- Framework
- Ollama
- Version
- v0.46
- Context length
- 8192 tokens
- Batch size
- 256
- GPU layers
- 33
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA H100 80GB HBM3
- Nominal VRAM
- 80 GB
- Measured VRAM (avg)
- 18.9 GB
- OS
- Ubuntu 22.04
- Driver
- 572.83
- CUDA
- 12.8
- Power draw
- 583 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.46 · Ubuntu 22.04 · CUDA 12.8 · 8192 ctx
301.71 tok/s
Decode
1,324.79 tok/s
Prefill
1 s
TTFT
18.9 GB
VRAM
—
MTP
583 W
Power draw
L2 batch seed 2026-10-19: Ollama on hw_id=55 running model_id=53 at Q6_K