Back to search results
Qwen3-1.7B · Q5_K_M
AMD Radeon RX 907016GBStrata v0.34L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-1.7B (Q5_K_M) on AMD Radeon RX 9070 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
186.72 tok/s
Decode
Decode speed
727.73 tok/s
Prefill
Prefill speed
1.31 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
5 days ago
Last verified
Performance
- llama.cpp · IQ1_S Decode 251.73 · Prefill 1075.85 ·
- llama.cpp · Q3_K_L Decode 168.28 · Prefill 901.02 ·
- Strata · IQ3_XS Decode 263.09 · Prefill 972.27 ·
- Strata · Q5_K_M (current)Decode 186.72 · Prefill 727.73 ·
Core figures
- Decode (avg)
- 186.72 tok/s
- Prefill (avg)
- 727.73 tok/s
- TTFT (avg)
- 1.31 s
- VRAM (avg)
- 5.42 GB
- MTP acceptance rate
- 0.54
- TTFB
- 1.49 GB
- Power draw
- 238.3 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-1.7B
- Quantization
- Q5_K_M
- Framework
- Strata
- Version
- v0.34
- Context length
- 32768 tokens
- Batch size
- 512
- GPU layers
- 8
- 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)
- 5.42 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 238.3 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.34 · Windows 11 23H2 · CUDA N/A · 32768 ctx
186.72 tok/s
Decode
727.73 tok/s
Prefill
1.31 s
TTFT
5.42 GB
VRAM
0.54
MTP
238.3 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=21 running model_id=55 at Q5_K_M