Back to search results
Qwen3-8B · IQ2_XS
NVIDIA RTX 4080 Super16GBllama.cpp v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (IQ2_XS) on NVIDIA RTX 4080 Super with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
195.22 tok/s
Decode
Decode speed
907.33 tok/s
Prefill
Prefill speed
1.39 s
TTFT
Time to first token
10.16 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 (current)Decode 195.22 · Prefill 907.33 ·
- vLLM · IQ2_M Decode 221.69 · Prefill 772.06 ·
Core figures
- Decode (avg)
- 195.22 tok/s
- Prefill (avg)
- 907.33 tok/s
- TTFT (avg)
- 1.39 s
- VRAM (avg)
- 10.16 GB
- MTP acceptance rate
- —
- TTFB
- 1.56 GB
- Power draw
- 278 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- IQ2_XS
- Framework
- llama.cpp
- Version
- v0.26
- 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 4080 Super
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 10.16 GB
- OS
- Ubuntu 24.04
- Driver
- 565.57
- CUDA
- 12.6
- Power draw
- 278 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · Ubuntu 24.04 · CUDA 12.6 · 32768 ctx
195.22 tok/s
Decode
907.33 tok/s
Prefill
1.39 s
TTFT
10.16 GB
VRAM
—
MTP
278 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=20 running model_id=53 at IQ2_XS