Back to search results
Qwen3-4B-Thinking-2507 · Q3_K_S
AMD Radeon RX 7800 XT16GBStrata v0.36L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q3_K_S) on AMD Radeon RX 7800 XT with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
167.4 tok/s
Decode
Decode speed
757.67 tok/s
Prefill
Prefill speed
1.07 s
TTFT
Time to first token
7.56 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 167.4 · Prefill 757.67 ·
- Strata · Q5_K_M Decode 122.13 · Prefill 641.14 ·
Core figures
- Decode (avg)
- 167.4 tok/s
- Prefill (avg)
- 757.67 tok/s
- TTFT (avg)
- 1.07 s
- VRAM (avg)
- 7.56 GB
- MTP acceptance rate
- 0.73
- TTFB
- 1.34 GB
- Power draw
- 280.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B-Thinking-2507
- Quantization
- Q3_K_S
- Framework
- Strata
- Version
- v0.36
- Context length
- 2048 tokens
- Batch size
- 256
- 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 7800 XT
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 7.56 GB
- OS
- Ubuntu 24.04
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 280.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.36 · Ubuntu 24.04 · CUDA N/A · 2048 ctx
167.4 tok/s
Decode
757.67 tok/s
Prefill
1.07 s
TTFT
7.56 GB
VRAM
0.73
MTP
280.4 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=31 running model_id=57 at Q3_K_S