Back to search results
Qwen3.8-9B · IQ4_XS
NVIDIA RTX 309024GBOllama v0.44L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (IQ4_XS) on NVIDIA RTX 3090 with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
98.13 tok/s
Decode
Decode speed
496.33 tok/s
Prefill
Prefill speed
0.72 s
TTFT
Time to first token
16.09 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · Q3_K_S Decode 130.89 · Prefill 575.17 ·
- Ollama · IQ4_XS (current)Decode 98.13 · Prefill 496.33 ·
Core figures
- Decode (avg)
- 98.13 tok/s
- Prefill (avg)
- 496.33 tok/s
- TTFT (avg)
- 0.72 s
- VRAM (avg)
- 16.09 GB
- MTP acceptance rate
- —
- TTFB
- 0.79 GB
- Power draw
- 409.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.44
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 28
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 3090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 16.09 GB
- OS
- Windows 11 23H2
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 409.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.44 · Windows 11 23H2 · CUDA 12.8 · 32768 ctx
98.13 tok/s
Decode
496.33 tok/s
Prefill
0.72 s
TTFT
16.09 GB
VRAM
—
MTP
409.2 W
Power draw
L2 batch seed 2026-10-10: Ollama on hw_id=2 running model_id=52 at IQ4_XS