Back to search results
Qwen2.5-Omni-3B · Q5_K_M
AMD Strix Halo (Radeon 8060S)Ollama v0.47L2 Cross-framework verified
This page aggregates 1 real-world runs of Qwen2.5-Omni-3B (Q5_K_M) on AMD Strix Halo (Radeon 8060S) with Ollama, contributed by 1 independent source platforms; metrics are averages of published measurements.
87.89 tok/s
Decode
Decode speed
401.06 tok/s
Prefill
Prefill speed
1.13 s
TTFT
Time to first token
7.96 GB
VRAM
VRAM usage
L2 Cross-framework verified
1
Measured runs
1
Independent sources
Other
Source platforms
2 days ago
Last verified
Performance
- llama.cpp · IQ4_XS Decode 127.7 · Prefill 503.71 ·
- Ollama · Q4_K_S Decode 115.67 · Prefill 506.03 ·
- Ollama · Q5_K_M (current)Decode 87.89 · Prefill 401.06 ·
Core figures
- Decode (avg)
- 87.89 tok/s
- Prefill (avg)
- 401.06 tok/s
- TTFT (avg)
- 1.13 s
- VRAM (avg)
- 7.96 GB
- MTP acceptance rate
- —
- TTFB
- 0.7 GB
- Power draw
- 75.5 W
Configuration
Member-level fields are taken from the most recent run
- Model
- Qwen2.5-Omni-3B
- Quantization
- Q5_K_M
- Framework
- Ollama
- Version
- v0.47
- Context length
- 2048 tokens
- Batch size
- 512
- GPU layers
- 28
- Flash Attention
- On
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)
- 7.96 GB
- OS
- macOS 15.0
- Driver
- 560.94
- CUDA
- N/A
- Power draw
- 75.5 W
Sources & evidence
1 measured records in total, each traceable to its original source
v0.47 · macOS 15.0 · CUDA N/A · 2048 ctx
87.89 tok/s
Decode
401.06 tok/s
Prefill
1.13 s
TTFT
7.96 GB
VRAM
—
MTP
75.5 W
Power draw
L2 batch seed 2026-10-16: Ollama on hw_id=87 running model_id=60 at Q5_K_M