Back to search results
Qwen3-4B · IQ4_XS
Intel Arc A770 16GB16GBvLLM v0.31L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (IQ4_XS) on Intel Arc A770 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
72.03 tok/s
Decode
Decode speed
234.09 tok/s
Prefill
Prefill speed
2.41 s
TTFT
Time to first token
8.32 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ4_XS (current)Decode 72.03 · Prefill 234.09 ·
- Strata · Q6_K Decode 68.88 · Prefill 245.03 ·
- llama.cpp · IQ1_S Decode 92.68 · Prefill 463.17 ·
- vLLM · Q5_K_S Decode 59.1 · Prefill 316.05 ·
Core figures
- Decode (avg)
- 72.03 tok/s
- Prefill (avg)
- 234.09 tok/s
- TTFT (avg)
- 2.41 s
- VRAM (avg)
- 8.32 GB
- MTP acceptance rate
- —
- TTFB
- 0.58 GB
- Power draw
- 218.8 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- IQ4_XS
- Framework
- vLLM
- Version
- v0.31
- Context length
- 2048 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
- Intel Arc A770 16GB
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 8.32 GB
- OS
- Windows 11 23H2
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 218.8 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.31 · Windows 11 23H2 · CUDA 12.6 · 2048 ctx
72.03 tok/s
Decode
234.09 tok/s
Prefill
2.41 s
TTFT
8.32 GB
VRAM
—
MTP
218.8 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=97 running model_id=54 at IQ4_XS