Back to search results
Qwen3-Embedding-0.6B · IQ2_XS
AMD Strix Halo (Radeon 8060S)vLLM v0.36L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (IQ2_XS) on AMD Strix Halo (Radeon 8060S) with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
355.91 tok/s
Decode
Decode speed
1,759.4 tok/s
Prefill
Prefill speed
0.94 s
TTFT
Time to first token
2.71 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ2_XS (current)Decode 355.91 · Prefill 1759.4 ·
- vLLM · IQ3_S Decode 267.01 · Prefill 1239.81 ·
- Strata · IQ3_S Decode 374.22 · Prefill 1937.23 ·
Core figures
- Decode (avg)
- 355.91 tok/s
- Prefill (avg)
- 1,759.4 tok/s
- TTFT (avg)
- 0.94 s
- VRAM (avg)
- 2.71 GB
- MTP acceptance rate
- —
- TTFB
- 2.85 GB
- Power draw
- 54 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- IQ2_XS
- Framework
- vLLM
- Version
- v0.36
- Context length
- 4096 tokens
- Batch size
- 32
- 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
- AMD Strix Halo (Radeon 8060S)
- Measured VRAM (avg)
- 2.71 GB
- OS
- macOS 15.0
- Driver
- 555.85
- CUDA
- N/A
- Power draw
- 54 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.36 · macOS 15.0 · CUDA N/A · 4096 ctx
355.91 tok/s
Decode
1,759.4 tok/s
Prefill
0.94 s
TTFT
2.71 GB
VRAM
—
MTP
54 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=87 running model_id=62 at IQ2_XS