Back to search results
Qwen3-4B · Q3_K_L
AMD Strix Point (Radeon 890M)Ollama v0.47L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-4B (Q3_K_L) on AMD Strix Point (Radeon 890M) with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
75.1 tok/s
Decode
Decode speed
314.07 tok/s
Prefill
Prefill speed
0.21 s
TTFT
Time to first token
8.15 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · FP16 Decode 36.08 · Prefill 186.22 ·
- vLLM · IQ2_XS Decode 112.83 · Prefill 404.8 ·
- Ollama · IQ4_XS Decode 68.56 · Prefill 288.08 ·
- Ollama · Q3_K_L (current)Decode 75.1 · Prefill 314.07 ·
Core figures
- Decode (avg)
- 75.1 tok/s
- Prefill (avg)
- 314.07 tok/s
- TTFT (avg)
- 0.21 s
- VRAM (avg)
- 8.15 GB
- MTP acceptance rate
- —
- TTFB
- 0.6 GB
- Power draw
- 71.1 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-4B
- Quantization
- Q3_K_L
- Framework
- Ollama
- Version
- v0.47
- Context length
- 16384 tokens
- Batch size
- 512
- 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)
- 8.15 GB
- OS
- macOS 15.0
- Driver
- amdgpu 6.10
- CUDA
- N/A
- Power draw
- 71.1 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.47 · macOS 15.0 · CUDA N/A · 16384 ctx
75.1 tok/s
Decode
314.07 tok/s
Prefill
0.21 s
TTFT
8.15 GB
VRAM
—
MTP
71.1 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=89 running model_id=54 at Q3_K_L