Back to search results
Qwen3.5-9B · IQ3_XS
2x AMD Strix HaloStrata v0.26L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (IQ3_XS) on 2x AMD Strix Halo with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.
234.55 tok/s
Decode
Decode speed
886.87 tok/s
Prefill
Prefill speed
0.55 s
TTFT
Time to first token
13.82 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- Ollama · FP16 Decode 58.36 · Prefill 233.8 ·
- Strata · IQ3_XS (current)Decode 234.55 · Prefill 886.87 ·
Core figures
- Decode (avg)
- 234.55 tok/s
- Prefill (avg)
- 886.87 tok/s
- TTFT (avg)
- 0.55 s
- VRAM (avg)
- 13.82 GB
- MTP acceptance rate
- 0.58
- TTFB
- 1.88 GB
- Power draw
- 65.4 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- IQ3_XS
- Framework
- Strata
- Version
- v0.26
- Context length
- 2048 tokens
- Batch size
- 512
- 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
- 2x AMD Strix Halo
- Measured VRAM (avg)
- 13.82 GB
- OS
- Windows 11 23H2
- Driver
- amdgpu-pro 24.20
- CUDA
- N/A
- Power draw
- 65.4 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.26 · Windows 11 23H2 · CUDA N/A · 2048 ctx
234.55 tok/s
Decode
886.87 tok/s
Prefill
0.55 s
TTFT
13.82 GB
VRAM
0.58
MTP
65.4 W
Power draw
L2 batch seed 2026-10-16: Strata on hw_id=88 running model_id=49 at IQ3_XS