Back to search results
Qwen3-Embedding-0.6B · Q3_K_L
AMD Ryzen AI Max+ 395128GBStrata v0.35L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-Embedding-0.6B (Q3_K_L) on AMD Ryzen AI Max+ 395 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
322.37 tok/s
Decode
Decode speed
1,428.17 tok/s
Prefill
Prefill speed
0.98 s
TTFT
Time to first token
3 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 · IQ1_S Decode 285.55 · Prefill 1529.78 ·
- Ollama · Q5_K_S Decode 220.14 · Prefill 748.53 ·
- vLLM · IQ3_XS Decode 324.5 · Prefill 1240.61 ·
- Strata · IQ2_M Decode 293.11 · Prefill 1444.58 ·
- Strata · Q3_K_L (current)Decode 322.37 · Prefill 1428.17 ·
Core figures
- Decode (avg)
- 322.37 tok/s
- Prefill (avg)
- 1,428.17 tok/s
- TTFT (avg)
- 0.98 s
- VRAM (avg)
- 3 GB
- MTP acceptance rate
- 0.57
- TTFB
- 2.58 GB
- Power draw
- 69 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-Embedding-0.6B
- Quantization
- Q3_K_L
- Framework
- Strata
- Version
- v0.35
- Context length
- 16384 tokens
- Batch size
- 1024
- GPU layers
- 15
- Flash Attention
- On
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Ryzen AI Max+ 395
- Nominal VRAM
- 128 GB
- Measured VRAM (avg)
- 3 GB
- OS
- Windows 11 23H2
- Driver
- AMD Adrenalin 25.10.1
- CUDA
- N/A
- Power draw
- 69 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.35 · Windows 11 23H2 · CUDA N/A · 16384 ctx
322.37 tok/s
Decode
1,428.17 tok/s
Prefill
0.98 s
TTFT
3 GB
VRAM
0.57
MTP
69 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=24 running model_id=62 at Q3_K_L