Back to search results
Qwen3-8B · IQ2_M
NVIDIA RTX 4080 Super16GBvLLM v0.28L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (IQ2_M) on NVIDIA RTX 4080 Super with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
221.69 tok/s
Decode
Decode speed
772.06 tok/s
Prefill
Prefill speed
0.65 s
TTFT
Time to first token
10.84 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ2_XS Decode 195.22 · Prefill 907.33 ·
- vLLM · IQ2_M (current)Decode 221.69 · Prefill 772.06 ·
Core figures
- Decode (avg)
- 221.69 tok/s
- Prefill (avg)
- 772.06 tok/s
- TTFT (avg)
- 0.65 s
- VRAM (avg)
- 10.84 GB
- MTP acceptance rate
- —
- TTFB
- 1.77 GB
- Power draw
- 292 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- IQ2_M
- Framework
- vLLM
- Version
- v0.28
- Context length
- 4096 tokens
- Batch size
- 16
- GPU layers
- 999
- 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)
- 10.84 GB
- OS
- Windows 11 23H2
- Driver
- 570.86
- CUDA
- 13.0
- Power draw
- 292 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.28 · Windows 11 23H2 · CUDA 13.0 · 4096 ctx
221.69 tok/s
Decode
772.06 tok/s
Prefill
0.65 s
TTFT
10.84 GB
VRAM
—
MTP
292 W
Power draw
L2 batch seed 2026-10-18: vLLM on hw_id=20 running model_id=53 at IQ2_M