Back to search results
Qwen3-4B-Thinking-2507 · IQ2_XS
AMD Radeon RX 9070 XT16GBvLLM v0.41L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B-Thinking-2507 (IQ2_XS) on AMD Radeon RX 9070 XT with vLLM, contributed by 1 independent source platforms; metrics are averages of published measurements.
186.6 tok/s
Decode
Decode speed
815.85 tok/s
Prefill
Prefill speed
1.44 s
TTFT
Time to first token
6.13 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- vLLM · IQ2_XS (current)Decode 186.6 · Prefill 815.85 ·
- vLLM · Q5_K_S Decode 103.28 · Prefill 532.39 ·
- Ollama · Q3_K_M Decode 127.72 · Prefill 433.24 ·
- Ollama · Q3_K_S Decode 126.74 · Prefill 598.67 ·
Core figures
- Decode (avg)
- 186.6 tok/s
- Prefill (avg)
- 815.85 tok/s
- TTFT (avg)
- 1.44 s
- VRAM (avg)
- 6.13 GB
- MTP acceptance rate
- —
- TTFB
- 1.49 GB
- Power draw
- 252 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B-Thinking-2507
- Quantization
- IQ2_XS
- Framework
- vLLM
- Version
- v0.41
- Context length
- 2048 tokens
- Batch size
- 32
- 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)
- 6.13 GB
- OS
- Ubuntu 24.04
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 252 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.41 · Ubuntu 24.04 · CUDA N/A · 2048 ctx
186.6 tok/s
Decode
815.85 tok/s
Prefill
1.44 s
TTFT
6.13 GB
VRAM
—
MTP
252 W
Power draw
L2 batch seed 2026-10-13: vLLM on hw_id=16 running model_id=57 at IQ2_XS