Back to search results
Qwen3-Embedding-0.6B · Q8_0
AMD Strix Point (Radeon 890M)vLLM v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q8_0) on AMD Strix Point (Radeon 890M) with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
112.43 tok/s
Decode
Decode speed
505.72 tok/s
Prefill
Prefill speed
2.37 s
TTFT
Time to first token
3.55 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 178.08 · Prefill 918.71 ·
- vLLM · Q8_0 (current)Decode 112.43 · Prefill 505.72 ·
- Strata · IQ2_M Decode 281.13 · Prefill 1305.8 ·
- Strata · IQ3_XS Decode 273.43 · Prefill 1002.15 ·
Core figures
- Decode (avg)
- 112.43 tok/s
- Prefill (avg)
- 505.72 tok/s
- TTFT (avg)
- 2.37 s
- VRAM (avg)
- 3.55 GB
- MTP acceptance rate
- —
- TTFB
- 0.9 GB
- Power draw
- 101.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- Q8_0
- Framework
- vLLM
- Version
- v0.26
- Context length
- 8192 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 Point (Radeon 890M)
- Measured VRAM (avg)
- 3.55 GB
- OS
- macOS 15.0
- Driver
- amdgpu 6.10
- CUDA
- N/A
- Power draw
- 101.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · macOS 15.0 · CUDA N/A · 8192 ctx
112.43 tok/s
Decode
505.72 tok/s
Prefill
2.37 s
TTFT
3.55 GB
VRAM
—
MTP
101.6 W
Power draw
L2 batch seed 2026-10-16: vLLM on hw_id=89 running model_id=62 at Q8_0