Back to search results
Qwen3-Coder-Next · IQ3_S
Intel Arc A770 16GB16GBvLLM v0.24L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Coder-Next (IQ3_S) on Intel Arc A770 16GB with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
59.18 tok/s
Decode
Decode speed
211.63 tok/s
Prefill
Prefill speed
0.44 s
TTFT
Time to first token
1.05 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 (current)Decode 59.18 · Prefill 211.63 ·
- vLLM · Q4_K_S Decode 48.96 · Prefill 207.46 ·
- Ollama · IQ2_XS Decode 65.52 · Prefill 349.07 ·
- Ollama · IQ3_XS Decode 57.03 · Prefill 252.47 ·
Core figures
- Decode (avg)
- 59.18 tok/s
- Prefill (avg)
- 211.63 tok/s
- TTFT (avg)
- 0.44 s
- VRAM (avg)
- 1.05 GB
- MTP acceptance rate
- —
- TTFB
- 0.47 GB
- Power draw
- 199 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Coder-Next
- Quantization
- IQ3_S
- Framework
- vLLM
- Version
- v0.24
- Context length
- 16384 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 A770 16GB
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 1.05 GB
- OS
- Windows 11 23H2
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 199 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.24 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx
59.18 tok/s
Decode
211.63 tok/s
Prefill
0.44 s
TTFT
1.05 GB
VRAM
—
MTP
199 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=97 running model_id=58 at IQ3_S