Back to search results
Qwen3.8-9B · Q3_K_M
NVIDIA RTX 4080 Super16GBOllama v0.54L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.8-9B (Q3_K_M) on NVIDIA RTX 4080 Super with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
141.22 tok/s
Decode
Decode speed
455.03 tok/s
Prefill
Prefill speed
0.79 s
TTFT
Time to first token
14.95 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ1_S Decode 204.16 · Prefill 1111.21 ·
- Ollama · IQ2_XS Decode 174.28 · Prefill 597.11 ·
- Ollama · Q3_K_M (current)Decode 141.22 · Prefill 455.03 ·
Core figures
- Decode (avg)
- 141.22 tok/s
- Prefill (avg)
- 455.03 tok/s
- TTFT (avg)
- 0.79 s
- VRAM (avg)
- 14.95 GB
- MTP acceptance rate
- —
- TTFB
- 1.13 GB
- Power draw
- 213.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.8-9B
- Quantization
- Q3_K_M
- Framework
- Ollama
- Version
- v0.54
- Context length
- 2048 tokens
- Batch size
- 256
- 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 4080 Super
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 14.95 GB
- OS
- Windows 11 23H2
- Driver
- 572.83
- CUDA
- 12.4
- Power draw
- 213.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.54 · Windows 11 23H2 · CUDA 12.4 · 2048 ctx
141.22 tok/s
Decode
455.03 tok/s
Prefill
0.79 s
TTFT
14.95 GB
VRAM
—
MTP
213.4 W
Power draw
L2 batch seed 2026-10-18: Ollama on hw_id=20 running model_id=52 at Q3_K_M