Back to search results
Qwen3-4B · Q5_K_M
AMD Radeon RX 7800 XT16GBStrata v0.38L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (Q5_K_M) on AMD Radeon RX 7800 XT with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
113.72 tok/s
Decode
Decode speed
542.93 tok/s
Prefill
Prefill speed
0.95 s
TTFT
Time to first token
9.91 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- Strata · Q5_K_M (current)Decode 113.72 · Prefill 542.93 ·
Core figures
- Decode (avg)
- 113.72 tok/s
- Prefill (avg)
- 542.93 tok/s
- TTFT (avg)
- 0.95 s
- VRAM (avg)
- 9.91 GB
- MTP acceptance rate
- 0.71
- TTFB
- 0.91 GB
- Power draw
- 248.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- Q5_K_M
- Framework
- Strata
- Version
- v0.38
- 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
- AMD Radeon RX 7800 XT
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 9.91 GB
- OS
- Ubuntu 24.04
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 248.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.38 · Ubuntu 24.04 · CUDA N/A · 16384 ctx
113.72 tok/s
Decode
542.93 tok/s
Prefill
0.95 s
TTFT
9.91 GB
VRAM
0.71
MTP
248.1 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=31 running model_id=54 at Q5_K_M