Back to search results
Qwen3-1.7B · Q3_K_L
AMD Strix Point (Radeon 890M)Strata v0.25L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q3_K_L) on AMD Strix Point (Radeon 890M) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
154.95 tok/s
Decode
Decode speed
755.86 tok/s
Prefill
Prefill speed
0.87 s
TTFT
Time to first token
4.67 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · Q8_0 Decode 68.66 · Prefill 239.32 ·
- Strata · Q3_K_L (current)Decode 154.95 · Prefill 755.86 ·
- Strata · Q4_K_M Decode 149.78 · Prefill 509.73 ·
Core figures
- Decode (avg)
- 154.95 tok/s
- Prefill (avg)
- 755.86 tok/s
- TTFT (avg)
- 0.87 s
- VRAM (avg)
- 4.67 GB
- MTP acceptance rate
- 0.62
- TTFB
- 1.24 GB
- Power draw
- 67.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q3_K_L
- Framework
- Strata
- Version
- v0.25
- 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 Strix Point (Radeon 890M)
- Measured VRAM (avg)
- 4.67 GB
- OS
- macOS 15.0
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 67.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.25 · macOS 15.0 · CUDA N/A · 16384 ctx
154.95 tok/s
Decode
755.86 tok/s
Prefill
0.87 s
TTFT
4.67 GB
VRAM
0.62
MTP
67.6 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=89 running model_id=55 at Q3_K_L