Back to search results
Qwen3-Embedding-0.6B · IQ4_XS
Intel Arc A770 16GB16GBOllama v0.46L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ4_XS) on Intel Arc A770 16GB with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
153.38 tok/s
Decode
Decode speed
732.92 tok/s
Prefill
Prefill speed
2.37 s
TTFT
Time to first token
3.03 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · Q4_K_S Decode 160.53 · Prefill 840.14 ·
- Ollama · IQ4_XS (current)Decode 153.38 · Prefill 732.92 ·
- Ollama · Q5_K_M Decode 116.05 · Prefill 477.94 ·
- Ollama · Q5_K_S Decode 121.2 · Prefill 454.65 ·
Core figures
- Decode (avg)
- 153.38 tok/s
- Prefill (avg)
- 732.92 tok/s
- TTFT (avg)
- 2.37 s
- VRAM (avg)
- 3.03 GB
- MTP acceptance rate
- —
- TTFB
- 1.23 GB
- Power draw
- 176.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.46
- Context length
- 16384 tokens
- Batch size
- 512
- GPU layers
- 20
- 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)
- 3.03 GB
- OS
- Windows 11 23H2
- Driver
- Intel Arc 31.0.101.5186
- CUDA
- 12.6
- Power draw
- 176.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.46 · Windows 11 23H2 · CUDA 12.6 · 16384 ctx
153.38 tok/s
Decode
732.92 tok/s
Prefill
2.37 s
TTFT
3.03 GB
VRAM
—
MTP
176.1 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=97 running model_id=62 at IQ4_XS