Back to search results
Qwen3-8B · Q8_0
AMD Strix Halo (Radeon 8060S)Ollama v0.37L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen3-8B (Q8_0) on AMD Strix Halo (Radeon 8060S) with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
48.28 tok/s
Decode
Decode speed
205.87 tok/s
Prefill
Prefill speed
1.03 s
TTFT
Time to first token
21.42 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- vLLM · IQ1_S Decode 127.84 · Prefill 540.46 ·
- vLLM · Q4_K_S Decode 94.74 · Prefill 425.68 ·
- Ollama · Q5_K_M Decode 64.59 · Prefill 334.15 ·
- Ollama · Q8_0 (current)Decode 48.28 · Prefill 205.87 ·
Core figures
- Decode (avg)
- 48.28 tok/s
- Prefill (avg)
- 205.87 tok/s
- TTFT (avg)
- 1.03 s
- VRAM (avg)
- 21.42 GB
- MTP acceptance rate
- —
- TTFB
- 0.39 GB
- Power draw
- 50.2 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen3-8B
- Quantization
- Q8_0
- Framework
- Ollama
- Version
- v0.37
- Context length
- 32768 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 Halo (Radeon 8060S)
- Measured VRAM (avg)
- 21.42 GB
- OS
- macOS 15.0
- Driver
- 555.85
- CUDA
- N/A
- Power draw
- 50.2 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.37 · macOS 15.0 · CUDA N/A · 32768 ctx
48.28 tok/s
Decode
205.87 tok/s
Prefill
1.03 s
TTFT
21.42 GB
VRAM
—
MTP
50.2 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=87 running model_id=53 at Q8_0