Qwen3-8B · Q8_0
This page aggregates 3 real-world runs of Qwen3-8B (Q8_0) on NVIDIA RTX 4090 with llama.cpp, contributed by 1 independent source platforms; metrics are averages of published measurements.
87.18 tok/s
Decode
Decode speed
465.1 tok/s
Prefill
Prefill speed
1.06 s
TTFT
Time to first token
17.31 GB
VRAM
VRAM usage
3
Measured runs
1
Independent sources
Other
Source platforms
2026-10-18
Last verified
Performance
- llama.cpp · Q4_K_M Decode 142.71 · Prefill 813.73 ·
- vLLM · IQ3_S Decode 161.14 · Prefill 813.02 ·
- llama.cpp · IQ1_S Decode 187.88 · Prefill 983.15 ·
- llama.cpp · Q8_0 (current)Decode 87.18 · Prefill 465.1 ·
- vLLM · Q2_K Decode 164.91 · Prefill 671.93 ·
- llama.cpp · Q6_K Decode 88.33 · Prefill 428.17 ·
- vLLM · Q4_K_S Decode 126.59 · Prefill 467.91 ·
- vLLM · Q8_0 Decode 76.65 · Prefill 513.21 ·
- Ollama · Q6_K Decode 82.66 · Prefill 332.47 ·
- llama.cpp · IQ4_XS Decode 112 · Prefill 1323 ·
- vLLM · IQ4_XS Decode 104 · Prefill 1176 ·
- vLLM · Q4_K_M Decode 96 · Prefill 1061 ·
- vLLM · Q5_K_M Decode 95 · Prefill 815 ·
- Ollama · Q4_K_M Decode 113 · Prefill 922 ·
- Ollama · Q5_K_M Decode 95 · Prefill 1090 ·
- llama.cpp · Q5_K_M Decode 133.3 · Prefill 999.8 ·
Core figures
- Decode (avg)
- 87.18 tok/s
- Prefill (avg)
- 465.1 tok/s
- TTFT (avg)
- 1.06 s
- VRAM (avg)
- 17.31 GB
- MTP acceptance rate
- —
- TTFB
- 0.68 GB
- Power draw
- 386.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q8_0
- Framework
- llama.cpp
- Version
- v0.29
- Context length
- 16384 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 4090
- Nominal VRAM
- 24 GB
- Measured VRAM (avg)
- 17.31 GB
- OS
- Ubuntu 24.04
- Driver
- 560.94
- CUDA
- 12.8
- Power draw
- 301.7 W
Sources & evidence
3 measured records in total, each traceable to its original source
v0.29 · Ubuntu 24.04 · CUDA 12.8 · 16384 ctx
82.94 tok/s
Decode
405.82 tok/s
Prefill
1.07 s
TTFT
21.42 GB
VRAM
—
MTP
301.7 W
Power draw
L2 batch seed 2026-10-18: llama.cpp on hw_id=1 running model_id=53 at Q8_0
v0.28 · Ubuntu 24.04 · CUDA 12.8 · 2048 ctx
87.21 tok/s
Decode
303.99 tok/s
Prefill
1.97 s
TTFT
21.42 GB
VRAM
—
MTP
471.1 W
Power draw
L2 batch seed 2026-10-10: llama.cpp on hw_id=1 running model_id=53 at Q8_0
b4200 · Linux · CUDA 12.6 · 4096 ctx
91.4 tok/s
Decode
685.5 tok/s
Prefill
0.15 s
TTFT
9.1 GB
VRAM
—
MTP
— W
Power draw
L0 理论估算(add-1000-records-batch3)