Back to search results
Qwen3.5-9B · Q4_K_S
NVIDIA RTX 408016GBOllama v0.25L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (Q4_K_S) on NVIDIA RTX 4080 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
71.83 tok/s
Decode
Decode speed
361.81 tok/s
Prefill
Prefill speed
1.53 s
TTFT
Time to first token
15.2 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Ollama · Q4_K_S (current)Decode 71.83 · Prefill 361.81 ·
Core figures
- Decode (avg)
- 71.83 tok/s
- Prefill (avg)
- 361.81 tok/s
- TTFT (avg)
- 1.53 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.57 GB
- Power draw
- 281.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- Q4_K_S
- Framework
- Ollama
- Version
- v0.25
- Context length
- 32768 tokens
- Batch size
- 256
- 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 4080
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 15.2 GB
- OS
- Windows 11 23H2
- Driver
- 570.86
- CUDA
- 12.6
- Power draw
- 281.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.25 · Windows 11 23H2 · CUDA 12.6 · 32768 ctx
71.83 tok/s
Decode
361.81 tok/s
Prefill
1.53 s
TTFT
15.2 GB
VRAM
—
MTP
281.5 W
Power draw
L2 batch seed 2026-10-13: Ollama on hw_id=41 running model_id=49 at Q4_K_S