Back to search results
Qwen3-1.7B · Q5_K_M
2x AMD Strix HaloStrata v0.28L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q5_K_M) on 2x AMD Strix Halo with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
284.45 tok/s
Decode
Decode speed
1,280.23 tok/s
Prefill
Prefill speed
1.89 s
TTFT
Time to first token
5.42 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 · Q5_K_S Decode 236.18 · Prefill 1075.25 ·
- Strata · Q5_K_M (current)Decode 284.45 · Prefill 1280.23 ·
- Strata · Q5_K_S Decode 326.25 · Prefill 1416.72 ·
Core figures
- Decode (avg)
- 284.45 tok/s
- Prefill (avg)
- 1,280.23 tok/s
- TTFT (avg)
- 1.89 s
- VRAM (avg)
- 5.42 GB
- MTP acceptance rate
- 0.48
- TTFB
- 2.28 GB
- Power draw
- 101.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q5_K_M
- Framework
- Strata
- Version
- v0.28
- Context length
- 16384 tokens
- Batch size
- 512
- 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
- 2x AMD Strix Halo
- Measured VRAM (avg)
- 5.42 GB
- OS
- Ubuntu 22.04
- Driver
- 560.94
- CUDA
- N/A
- Power draw
- 101.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.28 · Ubuntu 22.04 · CUDA N/A · 16384 ctx
284.45 tok/s
Decode
1,280.23 tok/s
Prefill
1.89 s
TTFT
5.42 GB
VRAM
0.48
MTP
101.7 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=88 running model_id=55 at Q5_K_M