Back to search results
Qwen3-4B-Thinking-2507 · Q3_K_S
AMD Radeon RX 907016GBvLLM v0.53L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (Q3_K_S) on AMD Radeon RX 9070 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
140.19 tok/s
Decode
Decode speed
769.84 tok/s
Prefill
Prefill speed
0.37 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
- vLLM · IQ3_S Decode 127.52 · Prefill 534.05 ·
- vLLM · Q3_K_S (current)Decode 140.19 · Prefill 769.84 ·
Core figures
- Decode (avg)
- 140.19 tok/s
- Prefill (avg)
- 769.84 tok/s
- TTFT (avg)
- 0.37 s
- VRAM (avg)
- 7.56 GB
- MTP acceptance rate
- —
- TTFB
- 1.12 GB
- Power draw
- 244.6 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B-Thinking-2507
- Quantization
- Q3_K_S
- Framework
- vLLM
- Version
- v0.53
- Context length
- 4096 tokens
- Batch size
- 8
- GPU layers
- 999
- 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)
- 7.56 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 244.6 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.53 · Windows 11 23H2 · CUDA N/A · 4096 ctx
140.19 tok/s
Decode
769.84 tok/s
Prefill
0.37 s
TTFT
7.56 GB
VRAM
—
MTP
244.6 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=21 running model_id=57 at Q3_K_S