Back to search results
Qwen3.5-9B · IQ4_XS
AMD Strix Point (Radeon 890M)Ollama v0.25L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3.5-9B (IQ4_XS) on AMD Strix Point (Radeon 890M) with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
46.77 tok/s
Decode
Decode speed
176.41 tok/s
Prefill
Prefill speed
0.84 s
TTFT
Time to first token
15.2 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ3_S Decode 65.94 · Prefill 339.59 ·
- Ollama · IQ3_XS Decode 62.85 · Prefill 248.56 ·
- Ollama · IQ4_XS (current)Decode 46.77 · Prefill 176.41 ·
Core figures
- Decode (avg)
- 46.77 tok/s
- Prefill (avg)
- 176.41 tok/s
- TTFT (avg)
- 0.84 s
- VRAM (avg)
- 15.2 GB
- MTP acceptance rate
- —
- TTFB
- 0.37 GB
- Power draw
- 67.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3.5-9B
- Quantization
- IQ4_XS
- Framework
- Ollama
- Version
- v0.25
- Context length
- 16384 tokens
- Batch size
- 256
- GPU layers
- 28
- Flash Attention
- Off
Hardware
Nominal and measured figures are shown side by side; whether it runs is the reader's call
- GPU
- AMD Strix Point (Radeon 890M)
- Measured VRAM (avg)
- 15.2 GB
- OS
- macOS 15.0
- Driver
- amdgpu 6.10
- CUDA
- N/A
- Power draw
- 67.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.25 · macOS 15.0 · CUDA N/A · 16384 ctx
46.77 tok/s
Decode
176.41 tok/s
Prefill
0.84 s
TTFT
15.2 GB
VRAM
—
MTP
67.2 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=89 running model_id=49 at IQ4_XS