Back to search results
Qwen3-4B · Q8_0
Intel Arc 140VvLLM v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (Q8_0) on Intel Arc 140V with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
42.86 tok/s
Decode
Decode speed
150.62 tok/s
Prefill
Prefill speed
1.87 s
TTFT
Time to first token
11.76 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ3_S Decode 80.06 · Prefill 290.03 ·
- vLLM · Q8_0 (current)Decode 42.86 · Prefill 150.62 ·
- Ollama · IQ1_S Decode 81.27 · Prefill 262.71 ·
- Ollama · Q4_K_M Decode 54.47 · Prefill 248.92 ·
Core figures
- Decode (avg)
- 42.86 tok/s
- Prefill (avg)
- 150.62 tok/s
- TTFT (avg)
- 1.87 s
- VRAM (avg)
- 11.76 GB
- MTP acceptance rate
- —
- TTFB
- 0.34 GB
- Power draw
- 179.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- Q8_0
- Framework
- vLLM
- Version
- v0.43
- Context length
- 2048 tokens
- Batch size
- 8
- 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
- Intel Arc 140V
- Measured VRAM (avg)
- 11.76 GB
- OS
- Ubuntu 24.04
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 179.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · Ubuntu 24.04 · CUDA 12.6 · 2048 ctx
42.86 tok/s
Decode
150.62 tok/s
Prefill
1.87 s
TTFT
11.76 GB
VRAM
—
MTP
179.8 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=98 running model_id=54 at Q8_0