Back to search results
Qwen3-8B · Q2_K
NVIDIA RTX 4060 Ti 16GB16GBllama.cpp v0.37L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q2_K) on NVIDIA RTX 4060 Ti 16GB with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
129.58 tok/s
Decode
Decode speed
532.02 tok/s
Prefill
Prefill speed
1.47 s
TTFT
Time to first token
11.34 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
Today
Last verified
Performance
- llama.cpp · IQ3_XS Decode 120.55 · Prefill 447.58 ·
- llama.cpp · Q2_K (current)Decode 129.58 · Prefill 532.02 ·
- vLLM · Q3_K_L Decode 108.14 · Prefill 543.11 ·
- vLLM · IQ3_XS Decode 103.03 · Prefill 480.63 ·
Core figures
- Decode (avg)
- 129.58 tok/s
- Prefill (avg)
- 532.02 tok/s
- TTFT (avg)
- 1.47 s
- VRAM (avg)
- 11.34 GB
- MTP acceptance rate
- —
- TTFB
- 1.04 GB
- Power draw
- 168.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q2_K
- Framework
- llama.cpp
- Version
- v0.37
- Context length
- 8192 tokens
- Batch size
- 512
- GPU layers
- 33
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 4060 Ti 16GB
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 11.34 GB
- OS
- Windows 11 24H2
- Driver
- 560.94
- CUDA
- 12.6
- Power draw
- 168.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · Windows 11 24H2 · CUDA 12.6 · 8192 ctx
129.58 tok/s
Decode
532.02 tok/s
Prefill
1.47 s
TTFT
11.34 GB
VRAM
—
MTP
168.5 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=3 running model_id=53 at Q2_K