Back to search results
Qwen3-8B · Q3_K_S
AMD Radeon RX 9070 GRE12GBStrata v0.35L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q3_K_S) on AMD Radeon RX 9070 GRE with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
124.72 tok/s
Decode
Decode speed
470.9 tok/s
Prefill
Prefill speed
0.85 s
TTFT
Time to first token
11.4 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Strata · Q3_K_S (current)Decode 124.72 · Prefill 470.9 ·
Core figures
- Decode (avg)
- 124.72 tok/s
- Prefill (avg)
- 470.9 tok/s
- TTFT (avg)
- 0.85 s
- VRAM (avg)
- 11.4 GB
- MTP acceptance rate
- 0.49
- TTFB
- 1 GB
- Power draw
- 316.7 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q3_K_S
- Framework
- Strata
- Version
- v0.35
- Context length
- 4096 tokens
- Batch size
- 512
- GPU layers
- 15
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Radeon RX 9070 GRE
- Nominal VRAM
- 12 GB
- Measured VRAM (avg)
- 11.4 GB
- OS
- macOS 15.0
- Driver
- amdgpu 6.11
- CUDA
- N/A
- Power draw
- 316.7 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.35 · macOS 15.0 · CUDA N/A · 4096 ctx
124.72 tok/s
Decode
470.9 tok/s
Prefill
0.85 s
TTFT
11.4 GB
VRAM
0.49
MTP
316.7 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=32 running model_id=53 at Q3_K_S