Back to search results
Qwen2.5-Omni-3B · Q4_K_S
AMD Radeon RX 907016GBvLLM v0.46L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q4_K_S) on AMD Radeon RX 9070 with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
147.81 tok/s
Decode
Decode speed
510.18 tok/s
Prefill
Prefill speed
2.1 s
TTFT
Time to first token
7.01 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
4 days ago
Last verified
Performance
- vLLM · Q4_K_S (current)Decode 147.81 · Prefill 510.18 ·
- vLLM · Q8_0 Decode 91.32 · Prefill 374.63 ·
- Strata · Q6_K Decode 126.97 · Prefill 623.22 ·
Core figures
- Decode (avg)
- 147.81 tok/s
- Prefill (avg)
- 510.18 tok/s
- TTFT (avg)
- 2.1 s
- VRAM (avg)
- 7.01 GB
- MTP acceptance rate
- —
- TTFB
- 1.18 GB
- Power draw
- 233.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- Q4_K_S
- Framework
- vLLM
- Version
- v0.46
- Context length
- 32768 tokens
- Batch size
- 16
- 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)
- 7.01 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu 6.11
- CUDA
- N/A
- Power draw
- 233.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.46 · Windows 11 23H2 · CUDA N/A · 32768 ctx
147.81 tok/s
Decode
510.18 tok/s
Prefill
2.1 s
TTFT
7.01 GB
VRAM
—
MTP
233.4 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=21 running model_id=60 at Q4_K_S