Back to search results
Qwen3.5-9B · Q3_K_S
AMD Radeon RX 9070 XT16GBvLLM v0.28L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (Q3_K_S) on AMD Radeon RX 9070 XT with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
113.68 tok/s
Decode
Decode speed
457.77 tok/s
Prefill
Prefill speed
0.42 s
TTFT
Time to first token
14.38 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · IQ1_S Decode 133.24 · Prefill 623.53 ·
- vLLM · Q3_K_S (current)Decode 113.68 · Prefill 457.77 ·
- Ollama · IQ2_XS Decode 124.46 · Prefill 417.76 ·
Core figures
- Decode (avg)
- 113.68 tok/s
- Prefill (avg)
- 457.77 tok/s
- TTFT (avg)
- 0.42 s
- VRAM (avg)
- 14.38 GB
- MTP acceptance rate
- —
- TTFB
- 0.91 GB
- Power draw
- 317.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- Q3_K_S
- Framework
- vLLM
- Version
- v0.28
- Context length
- 4096 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 XT
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 14.38 GB
- OS
- Ubuntu 24.04
- Driver
- amdgpu 6.11
- CUDA
- N/A
- Power draw
- 317.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.28 · Ubuntu 24.04 · CUDA N/A · 4096 ctx
113.68 tok/s
Decode
457.77 tok/s
Prefill
0.42 s
TTFT
14.38 GB
VRAM
—
MTP
317.5 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=16 running model_id=49 at Q3_K_S