Back to search results
Qwen3-8B · IQ2_XS
AMD Radeon RX 9070 XT16GBStrata v0.24L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (IQ2_XS) on AMD Radeon RX 9070 XT with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
192.63 tok/s
Decode
Decode speed
774.46 tok/s
Prefill
Prefill speed
2.22 s
TTFT
Time to first token
10.16 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
5 days ago
Last verified
Performance
- llama.cpp · Q4_K_S Decode 123.04 · Prefill 487.34 ·
- vLLM · Q2_K Decode 168.21 · Prefill 814.55 ·
- vLLM · IQ2_XS Decode 142.91 · Prefill 782.4 ·
- Strata · IQ2_XS (current)Decode 192.63 · Prefill 774.46 ·
Core figures
- Decode (avg)
- 192.63 tok/s
- Prefill (avg)
- 774.46 tok/s
- TTFT (avg)
- 2.22 s
- VRAM (avg)
- 10.16 GB
- MTP acceptance rate
- 0.72
- TTFB
- 1.54 GB
- Power draw
- 288.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- IQ2_XS
- Framework
- Strata
- Version
- v0.24
- Context length
- 8192 tokens
- Batch size
- 1024
- 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 9070 XT
- Nominal VRAM
- 16 GB
- Measured VRAM (avg)
- 10.16 GB
- OS
- macOS 15.0
- Driver
- amdgpu 6.10
- CUDA
- N/A
- Power draw
- 288.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.24 · macOS 15.0 · CUDA N/A · 8192 ctx
192.63 tok/s
Decode
774.46 tok/s
Prefill
2.22 s
TTFT
10.16 GB
VRAM
0.72
MTP
288.1 W
Power draw
L2 batch seed 2026-10-13: Strata on hw_id=16 running model_id=53 at IQ2_XS