Back to search results
Qwen3-Embedding-0.6B · Q2_K
NVIDIA RTX 509032GBStrata v0.24L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q2_K) on NVIDIA RTX 5090 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
350.56 tok/s
Decode
Decode speed
1,533.82 tok/s
Prefill
Prefill speed
1.55 s
TTFT
Time to first token
2.79 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 Decode 304.51 · Prefill 1432.77 ·
- vLLM · Q3_K_S Decode 322.2 · Prefill 1743.15 ·
- Strata · Q2_K (current)Decode 350.56 · Prefill 1533.82 ·
- Strata · Q5_K_M Decode 291.92 · Prefill 1133.9 ·
Core figures
- Decode (avg)
- 350.56 tok/s
- Prefill (avg)
- 1,533.82 tok/s
- TTFT (avg)
- 1.55 s
- VRAM (avg)
- 2.79 GB
- MTP acceptance rate
- 0.57
- TTFB
- 2.8 GB
- Power draw
- 305.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- Q2_K
- Framework
- Strata
- Version
- v0.24
- Context length
- 16384 tokens
- Batch size
- 256
- GPU layers
- 12
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- NVIDIA RTX 5090
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 2.79 GB
- OS
- macOS 15.0
- Driver
- 565.57
- CUDA
- 12.4
- Power draw
- 305.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.24 · macOS 15.0 · CUDA 12.4 · 16384 ctx
350.56 tok/s
Decode
1,533.82 tok/s
Prefill
1.55 s
TTFT
2.79 GB
VRAM
0.57
MTP
305.4 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=13 running model_id=62 at Q2_K