Back to search results
Qwen3-4B · Q4_K_S
AMD Radeon AI PRO R970032GBStrata v0.45L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (Q4_K_S) on AMD Radeon AI PRO R9700 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
204.13 tok/s
Decode
Decode speed
1,042.53 tok/s
Prefill
Prefill speed
1.02 s
TTFT
Time to first token
8.65 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Strata · Q4_K_S (current)Decode 204.13 · Prefill 1042.53 ·
Core figures
- Decode (avg)
- 204.13 tok/s
- Prefill (avg)
- 1,042.53 tok/s
- TTFT (avg)
- 1.02 s
- VRAM (avg)
- 8.65 GB
- MTP acceptance rate
- 0.49
- TTFB
- 1.63 GB
- Power draw
- 230.9 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- Q4_K_S
- Framework
- Strata
- Version
- v0.45
- Context length
- 16384 tokens
- Batch size
- 256
- 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 Radeon AI PRO R9700
- Nominal VRAM
- 32 GB
- Measured VRAM (avg)
- 8.65 GB
- OS
- macOS 15.0
- Driver
- amdgpu 6.11
- CUDA
- N/A
- Power draw
- 230.9 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.45 · macOS 15.0 · CUDA N/A · 16384 ctx
204.13 tok/s
Decode
1,042.53 tok/s
Prefill
1.02 s
TTFT
8.65 GB
VRAM
0.49
MTP
230.9 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=79 running model_id=54 at Q4_K_S