Back to search results
Qwen3-Embedding-0.6B · Q3_K_M
AMD Radeon RX 907016GBStrata v0.23L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q3_K_M) on AMD Radeon RX 9070 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
383.87 tok/s
Decode
Decode speed
1,815.17 tok/s
Prefill
Prefill speed
1.4 s
TTFT
Time to first token
2.96 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · IQ4_XS Decode 254.94 · Prefill 1358.71 ·
- llama.cpp · Q5_K_M Decode 203.72 · Prefill 927.46 ·
- Strata · Q3_K_M (current)Decode 383.87 · Prefill 1815.17 ·
Core figures
- Decode (avg)
- 383.87 tok/s
- Prefill (avg)
- 1,815.17 tok/s
- TTFT (avg)
- 1.4 s
- VRAM (avg)
- 2.96 GB
- MTP acceptance rate
- 0.46
- TTFB
- 3.07 GB
- Power draw
- 274.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- Q3_K_M
- Framework
- Strata
- Version
- v0.23
- Context length
- 2048 tokens
- Batch size
- 1024
- 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
- AMD Radeon RX 9070
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 2.96 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 274.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.23 · Windows 11 23H2 · CUDA N/A · 2048 ctx
383.87 tok/s
Decode
1,815.17 tok/s
Prefill
1.4 s
TTFT
2.96 GB
VRAM
0.46
MTP
274.3 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=21 running model_id=62 at Q3_K_M