Back to search results
Qwen3-1.7B · Q4_K_M
AMD Strix Point (Radeon 890M)Strata v0.43L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q4_K_M) on AMD Strix Point (Radeon 890M) with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
149.78 tok/s
Decode
Decode speed
509.73 tok/s
Prefill
Prefill speed
0.74 s
TTFT
Time to first token
5.03 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 Decode 154.95 · Prefill 755.86 ·
- Strata · Q4_K_M (current)Decode 149.78 · Prefill 509.73 ·
Core figures
- Decode (avg)
- 149.78 tok/s
- Prefill (avg)
- 509.73 tok/s
- TTFT (avg)
- 0.74 s
- VRAM (avg)
- 5.03 GB
- MTP acceptance rate
- 0.49
- TTFB
- 1.2 GB
- Power draw
- 78.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q4_K_M
- Framework
- Strata
- Version
- v0.43
- Context length
- 32768 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)
- 5.03 GB
- OS
- macOS 15.0
- Driver
- 555.85
- CUDA
- N/A
- Power draw
- 78.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.43 · macOS 15.0 · CUDA N/A · 32768 ctx
149.78 tok/s
Decode
509.73 tok/s
Prefill
0.74 s
TTFT
5.03 GB
VRAM
0.49
MTP
78.9 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=89 running model_id=55 at Q4_K_M