Back to search results
Qwen3.5-9B · Q5_K_M
NVIDIA RTX 509032GBOllama v0.34L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (Q5_K_M) on NVIDIA RTX 5090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
166 tok/s
Decode
Decode speed
599.13 tok/s
Prefill
Prefill speed
2.05 s
TTFT
Time to first token
19.68 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · Q2_K Decode 277.25 · Prefill 1119.33 ·
- Ollama · Q5_K_M (current)Decode 166 · Prefill 599.13 ·
Core figures
- Decode (avg)
- 166 tok/s
- Prefill (avg)
- 599.13 tok/s
- TTFT (avg)
- 2.05 s
- VRAM (avg)
- 19.68 GB
- MTP acceptance rate
- —
- TTFB
- 1.33 GB
- Power draw
- 469.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- Q5_K_M
- Framework
- Ollama
- Version
- v0.34
- Context length
- 2048 tokens
- Batch size
- 512
- GPU layers
- 28
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 19.68 GB
- OS
- Ubuntu 24.04
- Driver
- 570.86
- CUDA
- 12.6
- Power draw
- 469.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.34 · Ubuntu 24.04 · CUDA 12.6 · 2048 ctx
166 tok/s
Decode
599.13 tok/s
Prefill
2.05 s
TTFT
19.68 GB
VRAM
—
MTP
469.4 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=13 running model_id=49 at Q5_K_M